1
Your word
measured
“grew the usual vegetables”
Definitions come from WordNet, a hand-curated dictionary.
occurring or encountered or experienced or observed frequently or in accordance with regular practice or procedure
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“grew the usual vegetables”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
unusual is the dictionary opposite of usual, yet this model puts it closer than every one of the 1 synonym 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 usual.
unusual is the dictionary opposite of usual, yet this model puts it closer than every one of the 1 synonym 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 usual.
unusual is the dictionary opposite of usual, yet this model puts it closer than every one of the 1 synonym 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 usual.
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 usual. 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 usual. 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 usual. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.