INDEX
Explanations
mentions of law enforcement agencies and their activities
New Auto-Interp
Negative Logits
ÑģÑĤи
-0.17
URT
-0.16
.registry
-0.15
aniu
-0.14
usive
-0.14
LAY
-0.14
ãĥ³ãĥij
-0.14
ümÃ¼ÅŁ
-0.14
رÙĬÙħ
-0.14
oningen
-0.14
POSITIVE LOGITS
/security
0.16
essel
0.16
Aug
0.15
oran
0.15
elta
0.14
lands
0.14
ionale
0.14
าà¸ĺ
0.14
dom
0.14
sock
0.14
Activations Density 0.007%