INDEX
Explanations
topics related to crime, education, justice and racial issues
New Auto-Interp
Negative Logits
########.
-0.76
QMetaType
-0.76
\{\\-0.75
vägen
-0.72
виправивши
-0.69
waitKey
-0.64
commerciaux
-0.64
ьаж
-0.62
vician
-0.61
démocr
-0.60
POSITIVE LOGITS
violence
0.56
waukee
0.54
gor
0.51
violence
0.51
inner
0.50
tió
0.48
atrième
0.48
violent
0.47
زد
0.46
riot
0.45
Activations Density 0.135%