INDEX
Explanations
mentions of violent incidents involving police or criminal activities
New Auto-Interp
Negative Logits
onde
-0.17
otts
-0.17
apg
-0.15
Jun
-0.14
veyor
-0.14
302
-0.14
ylko
-0.14
اÙĦا
-0.14
Selection
-0.13
Constantin
-0.13
POSITIVE LOGITS
iac
0.17
unw
0.16
ValueCollection
0.15
innoc
0.15
ader
0.14
oppel
0.14
ê·¼
0.14
SharedPtr
0.14
innocent
0.14
etus
0.14
Activations Density 0.344%