INDEX
Explanations
references to law enforcement and related activities
New Auto-Interp
Negative Logits
VERR
-0.16
غ
-0.15
undler
-0.15
éļĨ
-0.14
wart
-0.14
enas
-0.14
DECLARE
-0.14
èĤ¡ä¸ľ
-0.14
Margins
-0.14
adin
-0.14
POSITIVE LOGITS
police
0.48
Police
0.42
cops
0.36
officer
0.35
officers
0.35
Police
0.35
policing
0.34
polic
0.31
law
0.31
YPD
0.29
Activations Density 0.440%