INDEX
Explanations
references to historical and religious beliefs of ancient cultures, particularly in relation to Judaism and monotheism
New Auto-Interp
Negative Logits
itu
-0.15
cus
-0.15
емон
-0.14
Truy
-0.14
HCI
-0.14
Pend
-0.14
kus
-0.14
jug
-0.14
oku
-0.14
chw
-0.13
POSITIVE LOGITS
akh
0.15
horizon
0.15
adden
0.14
atri
0.14
çıŃ
0.13
Tik
0.13
cores
0.13
iano
0.13
erson
0.12
ients
0.12
Activations Density 0.009%