INDEX
Explanations
phrases conveying exceptions or negations
Text followed by commas
New Auto-Interp
Negative Logits
"):
-1.18
'):
-1.10
":
-1.01
")));
-1.01
"){
-1.01
$")
-1.00
'){
-0.98
".
-0.98
’).
-0.98
%");
-0.96
POSITIVE LOGITS
,
2.45
(),
1.37
!,
1.24
?,
1.23
,
1.19
$,
1.18
،
1.13
,
1.13
.,
1.13
，
1.11
Activations Density 8.938%