INDEX
Explanations
terms related to fashion
New Auto-Interp
Negative Logits
(([
-0.45
jeg
-0.41
|||
-0.40
trustee
-0.39
daß
-0.38
stumped
-0.37
indeki
-0.37
Rudy
-0.37
leta
-0.35
Reihe
-0.35
POSITIVE LOGITS
Fashion
2.08
fashion
2.03
Fashion
1.98
fashion
1.97
FASHION
1.89
FASHION
1.71
fashions
1.38
ashion
1.29
ashions
1.25
moda
1.23
Activations Density 0.002%