INDEX
Explanations
technical terms related to programming and mathematics
New Auto-Interp
Negative Logits
.
-0.87
;
-0.82
,
-0.80
!
-0.69
Krakowie
-0.60
=
-0.58
picioare
-0.58
elsewhere
-0.57
is
-0.57
throughout
-0.56
POSITIVE LOGITS
"):
1.03
"),
0.97
'),
0.95
")
0.95
-
0.94
'},
0.94
'):
0.94
"){
0.94
')
0.92
")){
0.90
Activations Density 0.587%