INDEX
Explanations
references to luxury brands and consumer behavior in fashion
New Auto-Interp
Negative Logits
nl
-0.18
orian
-0.18
improvis
-0.17
attrs
-0.16
Towers
-0.15
.attrs
-0.15
REDIENT
-0.14
XE
-0.14
ns
-0.14
Magical
-0.14
POSITIVE LOGITS
Burb
0.34
designer
0.32
Bulg
0.32
Gu
0.32
Chanel
0.31
Louis
0.30
Hermes
0.28
Vers
0.28
Designer
0.27
Herm
0.26
Activations Density 0.213%