INDEX
Explanations
mentions of Osama bin Laden
New Auto-Interp
Negative Logits
eries
-0.84
aic
-0.75
Hearth
-0.72
Philadelphia
-0.71
Consumer
-0.69
Scot
-0.66
ĨĴ
-0.66
Reviewer
-0.66
Quadro
-0.65
Brew
-0.65
POSITIVE LOGITS
himself
1.03
Laden
0.99
addafi
0.97
assassinated
0.97
Hussein
0.92
abad
0.87
Jinping
0.85
zbollah
0.85
bin
0.85
massac
0.84
Activations Density 0.042%