INDEX
Explanations
references to significant events or performances in sports
New Auto-Interp
Negative Logits
avra
-0.16
oot
-0.15
/fontawesome
-0.14
плиÑĤ
-0.14
олом
-0.14
.defer
-0.13
ftime
-0.13
dent
-0.13
playing
-0.13
played
-0.13
POSITIVE LOGITS
pitching
0.32
pitches
0.30
Pitch
0.29
pitched
0.29
hurl
0.29
pitch
0.28
pitch
0.28
arm
0.28
ERA
0.27
arms
0.26
Activations Density 0.078%