INDEX
Explanations
statistics related to sports performance
New Auto-Interp
Negative Logits
ãĥįãĥ«
-0.17
orate
-0.14
ört
-0.14
orta
-0.14
askan
-0.14
atern
-0.14
emain
-0.14
ÃĹ↵↵
-0.13
ợ
-0.13
ording
-0.13
POSITIVE LOGITS
21
0.17
19
0.16
обов
0.15
26
0.15
nds
0.15
elez
0.15
31
0.15
ights
0.15
29
0.14
34
0.14
Activations Density 0.010%