INDEX
Explanations
instances of legal actions or charges related to incidents
New Auto-Interp
Negative Logits
659
-0.15
flat
-0.14
handled
-0.14
656
-0.14
cout
-0.14
flats
-0.14
elly
-0.14
op
-0.13
Flat
-0.13
Kop
-0.13
POSITIVE LOGITS
FOX
0.25
FOX
0.24
Ey
0.20
rollo
0.19
uLocal
0.19
viewer
0.18
LINK
0.18
WEB
0.18
Viewer
0.18
xfb
0.17
Activations Density 0.062%