INDEX
Explanations
instances of police involvement and crime-related incidents
New Auto-Interp
Negative Logits
Ekon
-0.16
št
-0.15
_macros
-0.15
èľĺèĽĽ
-0.15
catalog
-0.14
NGX
-0.14
PECT
-0.14
getDrawable
-0.14
MUX
-0.14
.gwt
-0.14
POSITIVE LOGITS
encent
0.16
cles
0.16
ÑĬ
0.15
and
0.15
enc
0.15
enn
0.15
line
0.15
ena
0.15
angan
0.14
žÃŃ
0.14
Activations Density 0.150%