INDEX
Explanations
references to violence against people and animals
New Auto-Interp
Negative Logits
problem
-0.36
improvement
-0.36
pu
-0.36
InSection
-0.35
patch
-0.35
emphasis
-0.35
improve
-0.34
XtraReports
-0.33
initComponents
-0.33
questão
-0.32
POSITIVE LOGITS
utafitiHapana
0.79
CanadaChoose
0.66
$_"
0.62
innocent
0.60
innoc
0.60
victim
0.59
Victim
0.57
victim
0.56
innoc
0.56
Victim
0.55
Activations Density 0.449%