INDEX
Explanations
references to law enforcement personnel
New Auto-Interp
Negative Logits
tal
-0.19
Offensive
-0.14
iger
-0.14
ammers
-0.14
offensive
-0.14
+offset
-0.14
aries
-0.14
ạng
-0.14
ancer
-0.14
सर
-0.14
POSITIVE LOGITS
icer
0.17
ãģĦãģŁ
0.17
cott
0.17
ically
0.16
466
0.16
holders
0.16
ettel
0.15
quo
0.15
/on
0.15
entlich
0.15
Activations Density 0.019%