INDEX
Explanations
references to biblical texts and historical claims about religious scriptures
New Auto-Interp
Negative Logits
/token
-0.17
Verse
-0.15
Vers
-0.15
immortal
-0.14
cref
-0.14
дÑı
-0.14
enge
-0.14
failing
-0.14
aub
-0.14
verse
-0.14
POSITIVE LOGITS
deut
0.25
Wisdom
0.24
Sept
0.20
Pent
0.20
Ket
0.19
Minor
0.19
targ
0.19
canonical
0.19
canon
0.19
books
0.19
Activations Density 0.059%