INDEX
Explanations
mentions of specific authors and their works
New Auto-Interp
Negative Logits
.opensource
-0.15
ulumi
-0.15
éric
-0.14
erah
-0.14
že
-0.14
echa
-0.14
erap
-0.14
omal
-0.14
stru
-0.14
ále
-0.13
POSITIVE LOGITS
writing
0.18
article
0.17
percept
0.16
wrote
0.16
himself
0.15
chronic
0.15
åĭ
0.14
__/
0.14
Gret
0.14
writes
0.14
Activations Density 0.101%