INDEX
Explanations
concepts related to religious figures and theological ideas
New Auto-Interp
Negative Logits
cmc
-0.18
tring
-0.16
overy
-0.15
cntl
-0.15
ifes
-0.15
displ
-0.14
luv
-0.14
ocl
-0.14
hest
-0.14
wn
-0.14
POSITIVE LOGITS
alink
0.18
.ads
0.15
ë¹Ī
0.15
MainFrame
0.14
inki
0.14
جا
0.14
änd
0.14
initely
0.14
ãĥ¼ãĥŀ
0.14
Bart
0.13
Activations Density 0.038%