INDEX
Explanations
mentions of saints and religious figures
New Auto-Interp
Negative Logits
FFE
-0.17
Alexand
-0.16
adera
-0.15
opup
-0.15
apo
-0.15
ADVERTISEMENT
-0.15
acob
-0.14
анÑĸÑĤ
-0.14
_$_
-0.14
ffective
-0.14
POSITIVE LOGITS
Joseph
0.19
Mary
0.17
Annunci
0.17
Theresa
0.17
Colum
0.17
Hed
0.17
Francis
0.16
591
0.16
ilda
0.16
Mein
0.16
Activations Density 0.046%