INDEX
Explanations
references to religious texts and specific scripture citations
New Auto-Interp
Negative Logits
erland
-0.17
artz
-0.16
omer
-0.14
lesia
-0.14
ustin
-0.14
weis
-0.14
/validation
-0.14
è´¥
-0.14
dig
-0.14
illos
-0.14
POSITIVE LOGITS
;line
0.16
-Core
0.15
Insensitive
0.15
ukkan
0.15
thouse
0.14
ç¦
0.14
ewan
0.14
itk
0.14
iversite
0.14
اÙĥÙħ
0.14
Activations Density 0.030%