INDEX
Explanations
mentions of religious figures, specifically "Christ."
references to Jesus Christ
New Auto-Interp
Negative Logits
ãĥ³ãĤ¸
-0.77
é¾
-0.74
phrine
-0.72
IFE
-0.69
TRY
-0.68
knives
-0.67
ACTION
-0.66
UX
-0.66
Yugoslavia
-0.65
à¸
-0.65
POSITIVE LOGITS
ophe
1.10
church
1.07
mast
1.04
isphere
0.92
lia
0.92
cruc
0.89
elin
0.86
alon
0.85
inez
0.84
iscopal
0.84
Activations Density 0.015%