INDEX
Explanations
details related to police activity and incident reports
New Auto-Interp
Negative Logits
Transparency
-0.15
çŃĴ
-0.15
riba
-0.15
FAULT
-0.14
ADE
-0.14
overall
-0.14
VERSE
-0.14
forum
-0.13
Dud
-0.13
ear
-0.13
POSITIVE LOGITS
nev
0.18
agy
0.16
ril
0.16
pch
0.15
$LANG
0.15
bé
0.14
geo
0.14
geometry
0.14
ypress
0.14
gL
0.13
Activations Density 0.022%