INDEX
Explanations
elements related to sports tournaments and match outcomes
New Auto-Interp
Negative Logits
ledo
-0.18
ÙĴع
-0.15
ippet
-0.15
ropp
-0.15
amera
-0.15
itures
-0.14
itura
-0.14
artz
-0.14
?><
-0.14
egie
-0.14
POSITIVE LOGITS
eru
0.17
vier
0.16
pid
0.15
aiser
0.14
Bat
0.14
.datab
0.14
Buster
0.14
_percentage
0.14
atel
0.14
utter
0.13
Activations Density 0.020%