INDEX
Explanations
instances of dialogue and commentary from coaches and players
New Auto-Interp
Negative Logits
inky
-0.17
osy
-0.15
ãĥ¼ãĥ³
-0.15
drv
-0.14
å±ħ
-0.14
зов
-0.14
agged
-0.14
طار
-0.14
dej
-0.14
unc
-0.13
POSITIVE LOGITS
hire
0.16
lesen
0.15
afil
0.14
mic
0.14
Mic
0.14
DP
0.14
swear
0.14
αιν
0.14
Virt
0.14
dá»ĭch
0.13
Activations Density 0.211%