INDEX
Explanations
references to the Vatican
mentions of the Vatican
New Auto-Interp
Negative Logits
lasses
-0.89
eworld
-0.83
ãģ¦
-0.81
pring
-0.80
served
-0.80
merce
-0.80
rg
-0.77
TRY
-0.77
haw
-0.75
pite
-0.75
POSITIVE LOGITS
Vatican
1.03
arium
0.84
brass
0.80
atican
0.78
pope
0.76
Leaks
0.75
Assassins
0.75
Patriarch
0.74
Francis
0.73
Pont
0.73
Activations Density 0.005%