INDEX
Explanations
numerical data or measurements related to clothing sizes and prices
New Auto-Interp
Negative Logits
/pub
-0.16
det
-0.15
,
-0.15
Pub
-0.15
pub
-0.15
bins
-0.14
det
-0.14
las
-0.14
anh
-0.14
ovice
-0.13
POSITIVE LOGITS
sold
0.22
sold
0.21
Sold
0.18
anyl
0.16
Sold
0.16
DonaldTrump
0.16
_sold
0.16
Canonical
0.15
irq
0.14
ÑĢÑĥп
0.14
Activations Density 0.002%