INDEX
Negative Logits
�ન
-0.08
Split
-0.08
MUST
-0.08
Darkness
-0.07
configurable
-0.07
黑
-0.07
onafhankelijk
-0.07
Join
-0.07
-Б
-0.07
negros
-0.07
POSITIVE LOGITS
unlikely
0.09
anymore
0.09
😉
0.09
😂
0.09
dealing
0.08
judging
0.08
değil
0.08
unfair
0.07
�
0.07
rather
0.07
Activations Density 0.113%