INDEX
Explanations
actions or events related to violence or conflict
New Auto-Interp
Negative Logits
semi
-0.41
plein
-0.41
OMITTED
-0.36
FrameLayout
-0.36
asantry
-0.35
Telefone
-0.35
showered
-0.35
ätz
-0.35
semi
-0.34
minder
-0.34
POSITIVE LOGITS
ImageContext
0.67
رشف
0.63
#+#
0.62
abestanden
0.60
BorderFactory
0.59
tartalomajánló
0.59
Chwiliwch
0.57
SequentialGroup
0.56
AndEndTag
0.55
addGap
0.54
Activations Density 0.542%