INDEX
Explanations
references to religious themes and concepts within the text
New Auto-Interp
Negative Logits
_NATIVE
-0.18
secular
-0.17
виÑĤ
-0.16
aktu
-0.15
Ä
-0.14
AGR
-0.14
inspace
-0.14
çĸ¾
-0.13
VG
-0.13
ivity
-0.13
POSITIVE LOGITS
мил
0.15
enties
0.15
.Values
0.14
adan
0.14
aire
0.14
.scalablytyped
0.14
sup
0.13
enza
0.13
sburg
0.13
rup
0.13
Activations Density 1.020%