1
Your word
measured
“I could perceive the ship coming over the horizon”
Definitions come from WordNet, a hand-curated dictionary.
to become aware of through the senses
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“I could perceive the ship coming over the horizon”
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 perceive, 1 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to perceive.
This model splits perceive into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to perceive.
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.
This model splits perceive into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
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 perceive. 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 perceive. That gap is the model’s own learned association.
This model splits perceive into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to perceive. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.