INDEX
Explanations
mentions of law enforcement or policing activities
New Auto-Interp
Negative Logits
steen
-0.21
Noir
-0.15
chung
-0.15
gebung
-0.15
UTE
-0.15
McB
-0.15
fixtures
-0.14
Kou
-0.14
ORS
-0.14
Rim
-0.14
POSITIVE LOGITS
anca
0.21
Manuals
0.15
LabelText
0.15
eras
0.15
ksi
0.14
agan
0.14
bsp
0.14
Uvs
0.14
Gran
0.14
tram
0.14
Activations Density 0.018%