INDEX
Explanations
references to religious figures or titles, specifically cardinals
references to Cardinals in various contexts
New Auto-Interp
Negative Logits
elling
-0.84
ramid
-0.83
chn
-0.83
pel
-0.77
yrinth
-0.77
bered
-0.76
elled
-0.76
TRY
-0.74
hov
-0.74
orship
-0.73
POSITIVE LOGITS
Cardinal
1.17
cardinal
0.98
Archbishop
0.96
XVI
0.78
Newman
0.77
Francis
0.74
itary
0.73
Ric
0.72
Seraph
0.72
Patriarch
0.72
Activations Density 0.010%