INDEX
Explanations
references to sports achievements and athlete statistics
New Auto-Interp
Negative Logits
u
-0.16
iro
-0.15
ayne
-0.14
ADO
-0.14
enes
-0.13
ado
-0.13
"
-0.13
en
-0.13
bin
-0.12
lain
-0.12
POSITIVE LOGITS
rencont
0.17
dikke
0.16
ürk
0.15
eskort
0.15
nackt
0.14
εβ
0.14
ÂŃs
0.14
vor
0.14
wiÄĻ
0.14
krev
0.14
Activations Density 0.326%