INDEX
Explanations
punctuation and formatting markers in legal and academic texts
New Auto-Interp
Negative Logits
fran
-0.76
numRows
-0.71
tps
-0.66
widetilde
-0.65
NED
-0.62
tup
-0.61
сомо
-0.60
Peters
-0.60
ered
-0.59
cara
-0.58
POSITIVE LOGITS
$;
1.33
;;;
1.23
;;;;
1.22
_;
1.19
}$;
1.11
+;
1.10
icolon
1.08
;;
1.08
.;
1.06
%;
1.05
Activations Density 0.280%