INDEX
Explanations
mention of creative writing and publishing activities
New Auto-Interp
Negative Logits
Clarkson
-0.17
urr
-0.15
REAM
-0.14
Poster
-0.14
shop
-0.13
379
-0.13
imd
-0.13
ëĬIJ
-0.13
mill
-0.13
urer
-0.13
POSITIVE LOGITS
author
0.23
Author
0.22
novel
0.21
novels
0.21
Writing
0.21
Authors
0.21
authors
0.20
Writer
0.20
authors
0.20
@author
0.20
Activations Density 0.405%