1
Your word
measured
“She got a lot of paintings from her uncle”
Definitions come from WordNet, a hand-curated dictionary.
come into the possession of something concrete or abstract
得る is Japanese for got, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Japanese headword, not a Japanese definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“She got a lot of paintings from her uncle”
Definitions come from WordNet, a hand-curated dictionary.
2 of those are a raw byte rather than a character: Qwen3 8B splits this word below the character, so no single token it sees is readable.
This panel splits 得る itself, not got — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
leave is the dictionary opposite of got, yet this model puts it closer than 28 of the 45 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to got, 2 of 8 also appear in the dictionary. 45 of 70 dictionary synonyms are in this build; the rest have no vector to compare yet.
leave is the dictionary opposite of got, yet this model puts it closer than 19 of the 45 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to got, 1 of 8 also appear in the dictionary. 45 of 70 dictionary synonyms are in this build; the rest have no vector to compare yet.
leave is the dictionary opposite of got, yet this model puts it closer than 24 of the 45 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to got, 1 of 8 also appear in the dictionary. 45 of 70 dictionary synonyms are in this build; the rest have no vector to compare yet.
Model neighbours are distributional, not dictionary synonyms. Two words can be close because they appear in similar sentences, which is why an antonym can outscore a synonym here.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to got. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to got. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to got. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.