INDEX
Explanations
words related to specific items or entities in different categories, such as meats, households, trees, embryos, cells, iPhones, buildings, gasoline, cars, courses, surfaces, objects, bacteria, targets, devices, enemies, printed books, and drivers
nouns associated with various physical entities or categories
New Auto-Interp
Negative Logits
atever
-0.75
ANC
-0.72
jri
-0.68
OLOG
-0.62
HCR
-0.61
charm
-0.60
urse
-0.60
ASY
-0.60
OOK
-0.59
ilogy
-0.59
POSITIVE LOGITS
undergoing
0.86
subjected
0.80
sampled
0.78
afflicted
0.75
ensitive
0.73
aged
0.73
receiving
0.70
exhibiting
0.70
alike
0.70
composing
0.69
Activations Density 0.419%