INDEX
Explanations
references to various contexts and conditions around discourse and language
Text surrounded by em dashes, stars, or commas
list separators or dashes
New Auto-Interp
Negative Logits
--}}
-1.33
***/
-1.27
*/
-1.25
]";
-1.21
)");
-1.20
.",
-1.19
};*/
-1.17
"]);
-1.17
.";
-1.16
"])
-1.16
POSITIVE LOGITS
--
1.18
—
1.06
–
1.05
---
0.90
•
0.86
——
0.80
~
0.79
=
0.77
-.
0.74
*
0.73
Activations Density 0.721%