INDEX
Explanations
references to sports teams and their performance
New Auto-Interp
Negative Logits
awai
-0.15
olf
-0.15
anga
-0.14
ÑģиÑĤ
-0.14
lyn
-0.14
zel
-0.14
iele
-0.14
institutional
-0.14
üz
-0.14
rest
-0.13
POSITIVE LOGITS
ÐľÐŀ
0.16
TERN
0.15
Slee
0.14
TU
0.13
McCart
0.13
lion
0.13
Sle
0.13
sleeper
0.13
گاÙĨ
0.13
InputElement
0.13
Activations Density 0.139%