INDEX
Negative Logits
.delivery
-0.07
lên
-0.07
udades
-0.06
perial
-0.06
(theta
-0.06
سد
-0.06
Eventually
-0.06
kv
-0.06
dru
-0.06
reconnaissance
-0.06
POSITIVE LOGITS
_comments
0.07
0.06
ACK
0.06
ンディ
0.06
excuse
0.06
.moves
0.06
undermines
0.06
başlat
0.06
卒
0.06
ΥΝ
0.06
Activations Density 0.009%