1
Your word
measured
“understanding protein folding is the next step in deciphering the genetic code”
Definitions come from WordNet, a hand-curated dictionary.
the process whereby a protein molecule assumes its intricate three-dimensional shape
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“understanding protein folding is the next step in deciphering the genetic code”
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 folding, 1 of 8 also appear in the dictionary. 2 of 11 dictionary synonyms are in this build; the rest have no vector to compare yet.
open is the dictionary opposite of folding, yet this model puts it closer than 1 of the 2 synonyms 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 folding, 1 of 8 also appear in the dictionary. 2 of 11 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits folding 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.
open is the dictionary opposite of folding, yet this model puts it closer than 1 of the 2 synonyms 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 folding, 1 of 8 also appear in the dictionary. 2 of 11 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.
This model splits folding 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 folding. 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 folding. That gap is the model’s own learned association.
This model splits folding 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 folding. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.