INDEX
Explanations
mentions of law enforcement agencies, specifically the FBI and the ATF
New Auto-Interp
Negative Logits
steen
-0.18
agh
-0.15
eti
-0.15
iants
-0.15
inou
-0.15
êµ´
-0.15
heim
-0.14
thon
-0.14
angen
-0.14
ierte
-0.14
POSITIVE LOGITS
mens
0.14
eger
0.14
.gov
0.14
Siz
0.14
zej
0.13
-NLS
0.13
ACP
0.13
MenuItem
0.13
artner
0.13
jde
0.13
Activations Density 0.007%