INDEX
Negative Logits
Gender
-0.08
ते
-0.08
ède
-0.08
Tän
-0.08
Médio
-0.08
_uniform
-0.07
Jewelry
-0.07
.Float
-0.07
flowers
-0.07
(TAG
-0.07
POSITIVE LOGITS
nerd
0.10
Debian
0.09
parody
0.09
aho
0.09
bière
0.09
knowledgeable
0.09
munk
0.08
Nerd
0.08
বান
0.08
rpm
0.08
Activations Density 0.019%