INDEX
Negative Logits
holdings
-0.09
sb
-0.08
-0.08
وط
-0.08
holds
-0.07
what's
-0.07
(material
-0.07
物
-0.07
(sb
-0.07
sb
-0.07
POSITIVE LOGITS
perror
0.13
Warning
0.13
.Errorf
0.13
_warning
0.13
.warning
0.12
warning
0.12
disappointed
0.12
warning
0.12
Warning
0.12
erreur
0.11
Activations Density 0.015%