INDEX
Explanations
references to the name "Osama bin Laden"
references to Osama bin Laden
New Auto-Interp
Negative Logits
mble
-0.75
pter
-0.71
hips
-0.71
anwhile
-0.71
laus
-0.69
ktop
-0.67
IRE
-0.65
âĢ¢âĢ¢
-0.65
ITH
-0.64
compr
-0.62
POSITIVE LOGITS
ocular
1.74
omial
1.70
Laden
1.62
nington
1.03
ational
0.96
jamin
0.95
ned
0.94
utils
0.92
ning
0.90
thood
0.90
Activations Density 0.057%