1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
the alliance of nations that fought the Axis in World War II and which (with subsequent additions) signed the charter of the United Nations in 1945
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
foe is the dictionary opposite of allies, yet this model puts it closer than 1 of the 2 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 allies, 1 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to allies, 1 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to allies.
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 allies. 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 allies. 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 allies. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.