INDEX
Explanations
references to Jesus Christ
New Auto-Interp
Negative Logits
thon
-0.17
lect
-0.16
ialized
-0.16
otos
-0.16
ECT
-0.15
cts
-0.14
icios
-0.14
ayet
-0.14
jah
-0.14
theless
-0.14
POSITIVE LOGITS
adel
0.25
ophe
0.23
like
0.22
ians
0.22
opher
0.20
mast
0.20
ains
0.20
otel
0.19
subpackage
0.19
church
0.19
Activations Density 0.013%