INDEX
Explanations
references to sports events, particularly focusing on golf
New Auto-Interp
Negative Logits
otch
-0.17
apiro
-0.16
Kanun
-0.15
iento
-0.15
ogo
-0.15
auc
-0.14
stry
-0.14
ropa
-0.14
oron
-0.14
@show
-0.14
POSITIVE LOGITS
afr
0.16
Interr
0.13
-meta
0.13
Constructors
0.13
alse
0.13
TRAIN
0.13
ewed
0.13
enberg
0.13
ayar
0.13
invol
0.13
Activations Density 0.018%