INDEX
Explanations
references to the word "Allah" in the text
references to religious figures and texts, particularly in an Islamic context
New Auto-Interp
Negative Logits
ENS
-0.84
Sturgeon
-0.72
ologne
-0.71
enegger
-0.70
Grimes
-0.70
ocamp
-0.67
Wilmington
-0.67
Jenner
-0.67
ilib
-0.66
SPONSORED
-0.66
POSITIVE LOGITS
abad
1.10
Almighty
1.02
selves
0.98
ĪĴ
0.87
uria
0.80
hammad
0.78
Allah
0.78
\\\\\\\\\\\\\\\\
0.77
Quran
0.77
istically
0.77
Activations Density 0.033%