INDEX
Explanations
references to biblical texts and numeric identifiers associated with them
New Auto-Interp
Negative Logits
unca
-0.16
æĽ
-0.16
thur
-0.14
.variant
-0.14
uzzi
-0.14
微软éĽħé»ij
-0.14
oun
-0.14
hazi
-0.14
alez
-0.14
st
-0.14
POSITIVE LOGITS
/th
0.18
-thirds
0.17
nd
0.17
ois
0.16
Roose
0.16
Nichols
0.15
andal
0.15
ãĢģä¸ī
0.15
LSB
0.15
peria
0.15
Activations Density 0.271%