INDEX
Explanations
references to Christ or Jesus in various contexts
New Auto-Interp
Negative Logits
sob
-0.17
icios
-0.15
ationale
-0.14
readcr
-0.14
ugs
-0.14
gett
-0.14
chsel
-0.14
651
-0.14
å¯
-0.13
lush
-0.13
POSITIVE LOGITS
ensen
0.33
church
0.31
ophe
0.30
opher
0.28
mast
0.27
ening
0.26
offer
0.25
enson
0.25
MAS
0.23
like
0.23
Activations Density 0.014%