INDEX
Explanations
references to golf tournaments and championships
New Auto-Interp
Negative Logits
inho
-0.17
gom
-0.15
agger
-0.15
ocus
-0.14
aurant
-0.14
oire
-0.14
utex
-0.14
atted
-0.14
iterals
-0.14
izzie
-0.14
POSITIVE LOGITS
ansa
0.17
-cn
0.16
visor
0.15
outu
0.15
outs
0.14
egl
0.14
ROP
0.14
ียม
0.14
ivor
0.14
ikt
0.14
Activations Density 0.002%