INDEX
Explanations
references to specific sports fields or stadiums
New Auto-Interp
Negative Logits
ilyn
-0.76
toget
-0.74
Lear
-0.67
bian
-0.65
CHAT
-0.64
compute
-0.64
charism
-0.64
ibilities
-0.64
Coch
-0.63
caut
-0.62
POSITIVE LOGITS
house
0.79
ert
0.79
ing
0.77
erton
0.77
enberg
0.74
backer
0.74
stadt
0.74
renheit
0.73
gart
0.73
Marshal
0.72
Activations Density 0.006%