INDEX
Explanations
references to biographies and personal reflections on individuals' lives
New Auto-Interp
Negative Logits
legen
-0.17
addock
-0.15
ainer
-0.15
ysts
-0.14
safeg
-0.14
arel
-0.14
wa
-0.14
alsex
-0.13
fol
-0.13
/downloads
-0.13
POSITIVE LOGITS
chapter
0.33
chapters
0.31
readers
0.31
reader
0.30
chapter
0.23
Readers
0.23
pages
0.23
Chapter
0.23
-reader
0.22
Chapters
0.22
Activations Density 0.129%