INDEX
Explanations
references to biblical scripture and related narratives
New Auto-Interp
Negative Logits
avern
-0.18
iphy
-0.18
ieux
-0.17
chia
-0.16
åĿIJ
-0.15
hung
-0.15
à¸ķร
-0.15
å¥ij
-0.15
SelectionMode
-0.14
rtl
-0.14
POSITIVE LOGITS
Peter
0.18
Peter
0.15
litt
0.15
Emma
0.15
scaling
0.14
Bett
0.14
Mara
0.14
dense
0.14
cling
0.14
uela
0.14
Activations Density 0.010%