INDEX
Negative Logits
prohibition
-0.08
separation
-0.08
desl
-0.08
(glm
-0.08
歉
-0.08
_le
-0.08
rim
-0.07
هئا
-0.07
led
-0.07
glomer
-0.07
POSITIVE LOGITS
zz
0.08
.languages
0.08
.edges
0.08
zd
0.08
.tail
0.07
emon
0.07
mucho
0.07
suggest
0.07
foreign
0.07
Intl
0.07
Activations Density 0.000%