INDEX
Explanations
mentions of the name "Christ" in various forms
New Auto-Interp
Negative Logits
556
-0.16
VRT
-0.16
vanished
-0.16
OUS
-0.15
thon
-0.15
ÑģÑı
-0.15
sob
-0.15
clist
-0.15
orman
-0.14
jis
-0.14
POSITIVE LOGITS
ensen
0.31
opher
0.28
ophe
0.26
enson
0.23
ening
0.21
like
0.20
offer
0.18
ened
0.17
ingle
0.17
offers
0.17
Activations Density 0.014%