INDEX
Explanations
descriptors related to quality and suitability of products
New Auto-Interp
Negative Logits
anzi
-0.15
153
-0.14
oppers
-0.14
courtesy
-0.14
embali
-0.14
ắng
-0.14
abei
-0.13
orias
-0.13
ymes
-0.13
nette
-0.13
POSITIVE LOGITS
choice
0.23
when
0.19
choice
0.19
/use
0.18
choices
0.18
whether
0.17
option
0.17
when
0.17
used
0.17
WHEN
0.17
Activations Density 0.091%