INDEX
Explanations
elements related to violence and crime
New Auto-Interp
Negative Logits
osta
-0.18
anzi
-0.16
anson
-0.15
tick
-0.15
Ngh
-0.15
akk
-0.14
:?
-0.14
uite
-0.14
nostr
-0.14
tit
-0.14
POSITIVE LOGITS
Karlov
0.15
axe
0.15
claims
0.15
DATE
0.14
coach
0.14
domicile
0.14
date
0.14
_msgs
0.14
_NOTIFY
0.14
EIF
0.13
Activations Density 0.313%