1
Your word
measured
“physicians should be held responsible for the health of their patients”
Definitions come from WordNet, a hand-curated dictionary.
a healthy state of wellbeing free from disease
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“physicians should be held responsible for the health of their patients”
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 health.
Shade shows how close the model puts each word to health.
illness is the dictionary opposite of health, 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 health.
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 health. 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 health. 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 health. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.