INDEX
Explanations
references to a significant entity or being, particularly in a religious context
New Auto-Interp
Negative Logits
arian
-0.17
izm
-0.15
nee
-0.15
ingt
-0.14
orman
-0.14
Medium
-0.14
erif
-0.14
zman
-0.13
e
-0.13
thew
-0.13
POSITIVE LOGITS
rencont
0.18
/her
0.18
SELF
0.17
hood
0.16
ë¦Ħ
0.15
æĪ²
0.15
ako
0.15
afd
0.15
Hood
0.14
dll
0.14
Activations Density 0.017%