INDEX
Explanations
elements of legal or formal documentation
New Auto-Interp
Negative Logits
NUMX
-1.02
")){
-1.00
"):
-0.96
"){
-0.93
'},
-0.93
"},
-0.93
")
-0.89
_
-0.88
'),
-0.87
"),
-0.84
POSITIVE LOGITS
.
1.12
;
1.08
!
1.02
,
1.01
?
0.82
:
0.67
!!
0.64
!!!
0.61
.*
0.60
。
0.59
Activations Density 1.642%