INDEX
Explanations
specific dates or references to time periods
New Auto-Interp
Negative Logits
eyen
-0.17
zung
-0.15
xCD
-0.15
OMIT
-0.14
herk
-0.14
ä¸įäºĨ
-0.14
gebung
-0.14
prostitutas
-0.14
ůr
-0.14
Ïģεια
-0.14
POSITIVE LOGITS
27
0.19
21
0.18
29
0.18
26
0.18
15
0.18
22
0.18
31
0.17
23
0.17
wick
0.17
-end
0.17
Activations Density 0.063%