INDEX
Explanations
references to the Pope and his actions or statements
New Auto-Interp
Negative Logits
prit
-0.17
Kingdom
-0.15
Wunused
-0.14
.Foundation
-0.14
isl
-0.14
amu
-0.14
nde
-0.14
igel
-0.14
oe
-0.13
odont
-0.13
POSITIVE LOGITS
curacy
0.17
endon
0.17
ervers
0.14
ALER
0.14
sher
0.14
elfast
0.13
footsteps
0.13
Ton
0.13
pher
0.13
odds
0.13
Activations Density 0.006%