INDEX
Explanations
names related to political figures and personalities
names of key political figures
New Auto-Interp
Negative Logits
chnology
-0.79
UNIVERS
-0.69
intendent
-0.67
nces
-0.66
Premium
-0.65
Seah
-0.64
itamin
-0.64
llular
-0.64
Wilmington
-0.63
Californ
-0.63
POSITIVE LOGITS
doms
1.32
Abdullah
1.17
dullah
0.97
hammad
0.90
iyah
0.88
ibn
0.86
istani
0.83
Hassan
0.83
edIn
0.82
istan
0.82
Activations Density 0.004%