INDEX
Explanations
references to shirts or related garments
New Auto-Interp
Negative Logits
enumi
-0.69
ทร
-0.59
wäh
-0.58
kasarigan
-0.57
phorbia
-0.55
LookAnd
-0.53
ValueStyle
-0.51
zel
-0.51
WebMethod
-0.50
au
-0.50
POSITIVE LOGITS
shirt
1.32
shirt
1.32
Shirt
1.31
Shirt
1.30
shirts
1.29
shirts
1.25
Shirts
1.22
Shirts
1.16
hirts
1.08
hirt
0.98
Activations Density 0.032%