INDEX
Explanations
elements related to crime and victimization
New Auto-Interp
Negative Logits
itori
-0.16
ink
-0.16
tha
-0.15
Urs
-0.15
izzard
-0.14
Kill
-0.14
inkel
-0.14
plag
-0.13
860
-0.13
éĮ
-0.13
POSITIVE LOGITS
被
0.34
éģŃ
0.32
被
0.29
being
0.28
being
0.26
åıĹåΰ
0.25
bá»ĭ
0.25
åıĹ
0.24
zosta
0.24
Being
0.23
Activations Density 0.214%