INDEX
Explanations
the occurrence of punctuation marks at the end of sentences
New Auto-Interp
Negative Logits
Rossi
-0.15
ogl
-0.15
uela
-0.15
ecta
-0.15
experiment
-0.14
eurs
-0.14
ertz
-0.14
plex
-0.14
esson
-0.13
mrt
-0.13
POSITIVE LOGITS
ntax
0.17
abcdefgh
0.15
ension
0.14
nuts
0.14
Capabilities
0.14
_thumb
0.13
ysa
0.13
vit
0.13
oj
0.13
agas
0.13
Activations Density 0.002%