INDEX
Explanations
phrases and religious statements indicating authority and prophecy
New Auto-Interp
Negative Logits
zin
-0.17
_YUV
-0.15
zc
-0.15
lette
-0.15
LETTE
-0.15
rang
-0.14
soc
-0.14
zbek
-0.14
몰
-0.14
Ñħо
-0.14
POSITIVE LOGITS
ery
0.16
asy
0.15
speedy
0.15
ient
0.15
CO
0.14
éli
0.14
rey
0.14
aire
0.14
Springer
0.14
ona
0.14
Activations Density 0.072%