INDEX
Explanations
references to religious or clerical figures and their influence on societal issues
New Auto-Interp
Negative Logits
ibe
-0.16
ibu
-0.16
å·¡
-0.15
ython
-0.15
Punk
-0.15
Ħ
-0.14
ittings
-0.14
Lutheran
-0.14
asure
-0.14
asca
-0.14
POSITIVE LOGITS
al
0.19
Wah
0.15
Al
0.15
Knights
0.15
erview
0.15
šak
0.15
Hat
0.15
Ans
0.14
šen
0.14
Swal
0.14
Activations Density 0.199%