INDEX
Explanations
words related to variety or difference
the concept of "different" in various contexts
New Auto-Interp
Negative Logits
ennes
-0.78
bows
-0.75
ENTS
-0.70
ULTS
-0.68
mates
-0.67
ammers
-0.67
mates
-0.66
ensibly
-0.64
ences
-0.64
md
-0.63
POSITIVE LOGITS
iator
1.26
iating
1.19
worldly
1.10
iates
1.10
dimension
0.92
kind
0.89
perspective
0.84
iable
0.83
subset
0.82
thing
0.81
Activations Density 0.053%