INDEX
Explanations
references to specific biblical texts and citations
New Auto-Interp
Negative Logits
amer
-0.17
logan
-0.15
Touches
-0.14
Gro
-0.14
andas
-0.14
utas
-0.14
Vien
-0.14
enaire
-0.14
jian
-0.14
assin
-0.14
POSITIVE LOGITS
butt
0.17
iger
0.15
angep
0.15
arah
0.14
Fam
0.14
tc
0.14
-popup
0.13
sg
0.13
uff
0.13
coordin
0.13
Activations Density 0.055%