INDEX
Explanations
references to religious or spiritual themes in texts
New Auto-Interp
Negative Logits
боÑĤ
-0.18
Hell
-0.15
pone
-0.15
ruz
-0.14
æİ¨
-0.14
ejs
-0.14
astro
-0.14
resse
-0.14
Sas
-0.14
ucer
-0.13
POSITIVE LOGITS
ps
0.34
Ps
0.33
Psalm
0.28
Ps
0.26
ps
0.25
PS
0.25
David
0.23
(ps
0.23
PS
0.23
David
0.21
Activations Density 0.037%