INDEX
Explanations
references to pain and suffering in a spiritual context
New Auto-Interp
Negative Logits
±
-0.15
legen
-0.15
bai
-0.14
podÃŃ
-0.14
utable
-0.14
fal
-0.14
ainer
-0.14
succinct
-0.13
plits
-0.13
Cleaning
-0.13
POSITIVE LOGITS
chapter
0.35
chapters
0.34
Chapter
0.27
chapter
0.26
Chapters
0.26
throughout
0.24
Chapter
0.23
reader
0.22
readers
0.22
Throughout
0.20
Activations Density 0.105%