INDEX
Negative Logits
buggy
-0.09
engager
-0.08
ینگ
-0.08
-focused
-0.08
Moms
-0.08
ggy
-0.08
celebrities
-0.08
dudes
-0.08
ulg
-0.08
总书记
-0.08
POSITIVE LOGITS
-between
0.10
between
0.09
між
0.08
separators
0.08
tussen
0.08
phakathi
0.08
Separator
0.08
汽
0.08
Between
0.08
between
0.08
Activations Density 0.010%