INDEX
Explanations
references to police and law enforcement
New Auto-Interp
Negative Logits
Vapor
-0.17
çĥ
-0.15
lej
-0.15
lay
-0.14
ulner
-0.14
ilee
-0.14
))==
-0.14
agens
-0.14
outu
-0.14
afia
-0.14
POSITIVE LOGITS
ppo
0.17
SKTOP
0.17
ighter
0.16
creen
0.16
inge
0.15
iasi
0.15
handgun
0.14
خرÙī
0.14
ObjectId
0.14
anda
0.14
Activations Density 0.018%