INDEX
Explanations
references to sports events and match outcomes
New Auto-Interp
Negative Logits
ænd
-0.17
umo
-0.17
ê·ł
-0.16
ıda
-0.15
strup
-0.15
Canter
-0.15
sson
-0.15
homosex
-0.14
ords
-0.14
Father
-0.14
POSITIVE LOGITS
.Err
0.16
Vand
0.16
Sor
0.15
Mug
0.15
gravity
0.15
iske
0.14
wt
0.14
sor
0.14
655
0.14
icans
0.14
Activations Density 0.006%