1
Your word
measured
“fatigue sapped his strength”
Definitions come from WordNet, a hand-curated dictionary.
the property of being physically or mentally strong
強さ is Japanese for strength, 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.
“fatigue sapped his strength”
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 強さ itself, not strength — 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.
weakness is the dictionary opposite of strength, yet this model puts it closer than 7 of the 8 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 strength, 1 of 8 also appear in the dictionary. 8 of 21 dictionary synonyms are in this build; the rest have no vector to compare yet.
weakness is the dictionary opposite of strength, yet this model puts it closer than every one of the 8 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 strength. 8 of 21 dictionary synonyms are in this build; the rest have no vector to compare yet.
weakness is the dictionary opposite of strength, yet this model puts it closer than every one of the 8 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 strength. 8 of 21 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 strength. 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 strength. 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 strength. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.