INDEX
Explanations
references to specific names or terms associated with the field of criminology
New Auto-Interp
Negative Logits
ards
-0.16
ied
-0.15
escal
-0.15
massaggi
-0.15
ths
-0.15
undry
-0.14
portun
-0.14
lied
-0.14
auty
-0.14
tar
-0.14
POSITIVE LOGITS
cr
0.23
Cr
0.22
ITICAL
0.22
utch
0.19
ven
0.18
ystal
0.18
igslist
0.17
(cr
0.17
ystals
0.17
acro
0.17
Activations Density 0.026%