INDEX
Explanations
references to incidents of violence, particularly shootings
New Auto-Interp
Negative Logits
Tel
-0.15
na
-0.14
Ga
-0.14
ãĥijãĥ³
-0.14
Hew
-0.14
Om
-0.14
Continue
-0.14
inue
-0.14
Mast
-0.14
Kok
-0.13
POSITIVE LOGITS
akov
0.18
apore
0.17
ahas
0.16
æĸ½
0.15
prung
0.14
dün
0.14
á»ķng
0.14
Eigen
0.14
ucci
0.13
ivicrm
0.13
Activations Density 0.305%