1
Your word
measured
“I need to give it a good think”
Definitions come from WordNet, a hand-curated dictionary.
an instance of deliberate thinking
以为 is Chinese for think, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Chinese headword, not a Chinese definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“I need to give it a good think”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits 以为 itself, not think — 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.
forget is the dictionary opposite of think, yet this model puts it closer than 3 of the 11 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 think, 1 of 8 also appear in the dictionary. 11 of 18 dictionary synonyms are in this build; the rest have no vector to compare yet.
forget is the dictionary opposite of think, yet this model puts it closer than 3 of the 11 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 think, 1 of 8 also appear in the dictionary. 11 of 18 dictionary synonyms are in this build; the rest have no vector to compare yet.
forget is the dictionary opposite of think, yet this model puts it closer than 3 of the 11 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 think, 3 of 8 also appear in the dictionary. 11 of 18 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 think. 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 think. 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 think. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.