INDEX
Explanations
incidents involving crime and violent acts
New Auto-Interp
Negative Logits
hr
-0.15
ervo
-0.14
329
-0.14
mam
-0.14
hta
-0.14
igli
-0.14
ibr
-0.14
OfClass
-0.14
ichten
-0.14
ertiary
-0.13
POSITIVE LOGITS
uji
0.16
endants
0.16
iya
0.15
ç¿Ķ
0.14
iyan
0.14
ÐľÐŀ
0.14
_strerror
0.13
iy
0.13
å±¥
0.13
Ð¤ÐĽ
0.13
Activations Density 0.015%