INDEX
Explanations
intensifiers or modifiers that denote emphasis or contrast within narratives
New Auto-Interp
Negative Logits
erli
-0.17
blr
-0.14
allon
-0.14
jen
-0.13
arest
-0.13
ones
-0.13
.DAL
-0.13
ä¸įäºĨ
-0.13
ivate
-0.13
asure
-0.13
POSITIVE LOGITS
another
0.17
otra
0.17
eer
0.17
autre
0.15
ика
0.15
esc
0.15
reve
0.15
outra
0.14
different
0.14
าย
0.14
Activations Density 0.189%