INDEX
Negative Logits
andoned
-0.08
الش
-0.08
inutil
-0.08
442
-0.08
449
-0.08
punctuation
-0.07
788
-0.07
implanted
-0.07
384
-0.07
แน
-0.07
POSITIVE LOGITS
scaling
0.08
Scaling
0.08
Scaling
0.08
caling
0.08
houses
0.08
Fro
0.08
nephew
0.07
Ursachen
0.07
halve
0.07
_scal
0.07
Activations Density 0.001%