INDEX
Explanations
references to competitive achievements or milestones in sports and events
New Auto-Interp
Negative Logits
unken
-0.16
ail
-0.14
209
-0.14
ichten
-0.14
dao
-0.14
íĽ
-0.14
982
-0.14
ülük
-0.14
OKEN
-0.13
atos
-0.13
POSITIVE LOGITS
identical
0.33
same
0.30
same
0.26
_same
0.25
Same
0.24
SAME
0.24
exactly
0.24
Same
0.23
SAME
0.23
åIJĮãģĺ
0.23
Activations Density 0.070%