INDEX
Explanations
phrases related to religious figures and their actions
references to religious or prophetic figures
New Auto-Interp
Negative Logits
icia
-0.79
ucha
-0.73
HG
-0.68
hern
-0.67
ens
-0.66
umbers
-0.66
ILA
-0.66
icky
-0.65
ilde
-0.65
iw
-0.64
POSITIVE LOGITS
Prophet
4.05
prophet
2.68
Messenger
2.40
Prophe
2.12
Apostle
2.04
prophets
1.94
Quran
1.72
Koran
1.55
apostle
1.51
Qur
1.47
Activations Density 0.026%