INDEX
Explanations
references to sports and competitive contexts
New Auto-Interp
Negative Logits
alone
-0.17
wood
-0.16
ÙĪÙĦÛĮ
-0.15
BarButtonItem
-0.15
alone
-0.15
499
-0.15
umo
-0.15
atu
-0.15
loo
-0.15
apper
-0.14
POSITIVE LOGITS
istring
0.14
auge
0.14
vetica
0.14
vore
0.14
stride
0.14
bilt
0.14
Pago
0.13
chwitz
0.13
obraz
0.13
argo
0.13
Activations Density 0.206%