INDEX
Explanations
numerical values in various contexts
New Auto-Interp
Negative Logits
Bry
-0.19
rez
-0.17
tet
-0.16
illaume
-0.15
ãģŃ
-0.15
éϽ
-0.15
oyer
-0.14
quez
-0.14
yster
-0.14
Blake
-0.14
POSITIVE LOGITS
30
0.57
030
0.39
Û³Û°
0.37
thirty
0.31
230
0.28
Thirty
0.28
130
0.26
730
0.25
930
0.24
630
0.24
Activations Density 0.047%