1
Your word
measured
“his story brought tears to her eyes”
Definitions come from WordNet, a hand-curated dictionary.
a drop of the clear salty saline solution secreted by the lacrimal glands
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“his story brought tears to her eyes”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to tear. 10 of 19 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to tear, 1 of 8 also appear in the dictionary. 10 of 19 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to tear, 2 of 8 also appear in the dictionary. 10 of 19 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 tear. 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 tear. 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 tear. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.