INDEX
Explanations
references to divine authority and traditional values in discussions about societal norms
New Auto-Interp
Negative Logits
Vo
-0.17
ito
-0.16
Vo
-0.15
abei
-0.15
hypo
-0.15
émon
-0.14
aches
-0.14
(summary
-0.14
uno
-0.14
Vill
-0.14
POSITIVE LOGITS
pell
0.15
aukee
0.15
Hear
0.15
~>
0.14
CRY
0.14
Blasio
0.14
stru
0.14
<!--[
0.14
оÑģÑĤи
0.13
ibri
0.13
Activations Density 0.319%