1
Your word
measured
“they emerged from the woods onto a vast open plain”
Definitions come from WordNet, a hand-curated dictionary.
extensive tract of level open land
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“they emerged from the woods onto a vast open plain”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
fancy is the dictionary opposite of plain, yet this model puts it closer than 12 of the 15 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 plain. 15 of 31 dictionary synonyms are in this build; the rest have no vector to compare yet.
fancy is the dictionary opposite of plain, yet this model puts it closer than 13 of the 15 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 plain. 15 of 31 dictionary synonyms are in this build; the rest have no vector to compare yet.
fancy is the dictionary opposite of plain, yet this model puts it closer than 9 of the 15 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 plain. 15 of 31 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 plain. 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 plain. 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 plain. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.