INDEX

Explanations

math notation with parentheses

function calls and math notation

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

キュー

0.45

 яхшы

0.42

 или

0.42

😼

0.40

✗

0.40

}).

0.39

 或者

0.39

Какие

0.38

 کیونکہ

0.38

ukam

0.38

POSITIVE LOGITS

()

0.73

({

0.67

()(

0.65

()")

0.63

(\{

0.63

();//

0.61

(...

0.61

()}\

0.61

():

0.60

Activations Density 0.006%