INDEX
Explanations
references to historical religious figures and saints
New Auto-Interp
Negative Logits
ë§ī
-0.07
577
-0.07
ضÙĬ
-0.07
436
-0.07
εÏĦ
-0.07
tring
-0.06
ffen
-0.06
umbn
-0.06
spender
-0.06
ourcem
-0.06
POSITIVE LOGITS
Lindsey
0.07
martyr
0.07
Marty
0.07
legend
0.07
unan
0.06
marty
0.06
Latin
0.06
Metro
0.06
Magnus
0.06
imi
0.06
Activations Density 0.007%