INDEX
Explanations
references to gun violence or shootings
New Auto-Interp
Negative Logits
licht
-0.16
FetchType
-0.15
angi
-0.15
rez
-0.14
edback
-0.14
braco
-0.14
gages
-0.14
ddit
-0.14
orial
-0.13
Funds
-0.13
POSITIVE LOGITS
fire
1.03
fired
0.93
firing
0.91
fire
0.86
fires
0.84
Fire
0.83
-fire
0.82
Fire
0.79
Fired
0.71
.fire
0.70
Activations Density 0.032%