INDEX
Explanations
numerical data and specific identifiers
dates or times
dates, numbers, and websites
New Auto-Interp
Negative Logits
."));
-1.41
?");
-1.38
?')
-1.36
?")
-1.36
:");
-1.30
?";
-1.28
?
-1.28
...");
-1.28
.",
-1.28
".
-1.25
POSITIVE LOGITS
|
1.96
-
1.67
/
1.54
–
1.53
|
1.39
||
1.29
//
1.28
•
1.25
—
1.17
·
1.16
Activations Density 0.789%