INDEX
Explanations
comparisons between fashion and other contexts, particularly focusing on standards and norms
New Auto-Interp
Negative Logits
oÄŁ
-0.16
baz
-0.14
yna
-0.13
ÙĪØ¦
-0.13
oj
-0.13
ika
-0.13
âte
-0.13
eton
-0.13
íĤ
-0.13
allis
-0.12
POSITIVE LOGITS
other
0.50
other
0.39
elsewhere
0.39
åħ¶ä»ĸ
0.35
OTHER
0.33
otras
0.33
autres
0.33
andere
0.32
'autres
0.31
Other
0.31
Activations Density 0.725%