INDEX
Explanations
phrases indicating economic or financial activities
New Auto-Interp
Negative Logits
odor
-0.15
iquement
-0.14
YG
-0.14
owers
-0.14
opo
-0.13
reen
-0.13
iku
-0.13
oidal
-0.13
scales
-0.13
ork
-0.13
POSITIVE LOGITS
pone
0.17
rez
0.16
ocoder
0.15
onto
0.15
Ideas
0.15
izm
0.14
è«
0.14
uis
0.14
tog
0.14
Kis
0.14
Activations Density 0.055%