INDEX
Explanations
team names and their associated performances or predictions in sports contexts
New Auto-Interp
Negative Logits
agli
-0.17
onio
-0.16
avanaugh
-0.14
synthesize
-0.14
ref
-0.14
ollen
-0.14
sum
-0.14
YD
-0.14
contro
-0.14
ł
-0.13
POSITIVE LOGITS
ilent
0.15
unsch
0.14
asis
0.14
apter
0.14
ernals
0.13
adına
0.13
hyth
0.13
zdy
0.13
ations
0.13
ÄĽti
0.13
Activations Density 0.047%