1
Your word
measured
“You deserve a promotion after all the hard work you have done”
Definitions come from WordNet, a hand-curated dictionary.
be worthy or deserving
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“You deserve a promotion after all the hard work you have done”
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 deserve.
Shade shows how close the model puts each word to deserve, 1 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to deserve.
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 deserve. 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 deserve. 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 deserve. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.