INDEX
Explanations
various numerical data and statistical values within the text
Numbers immediately following a word
numbers, time spans, quantities
New Auto-Interp
Negative Logits
uz
-0.47
rhosis
-0.44
aly
-0.42
uri
-0.42
ooo
-0.42
usr
-0.42
ank
-0.41
mann
-0.40
Liz
-0.40
ity
-0.39
POSITIVE LOGITS
propOrder
0.90
تقاوى
0.89
)");
0.89
)";
0.87
مشين
0.85
ParallelGroup
0.80
>");
0.79
}?>
0.78
")){
0.78
"]);
0.77
Activations Density 0.419%