INDEX

Explanations

code comments and file headers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</h4>

-2.14

</b>

-2.14

</h5>

-2.06

蕻

-1.84

</h2>

-1.73

 remé

-1.59

 diki

-1.51

 perpé

-1.48

 incrí

-1.48

 raconter

-1.46

POSITIVE LOGITS

 with

1.90

 They

1.83

 mereka

1.76

 their

1.61

 from

1.59

and

1.48

Perhaps

1.45

 Their

1.44

Their

1.42

 Some

1.41

Activations Density 0.054%