INDEX

Explanations

Tol prefix or part of names

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

 techniczne

-3.25

骋

-2.72

 природа

-2.69

 белая

-2.58

 новая

-2.55

 черная

-2.55

箆

-2.53

 esconde

-2.52

 ehemalige

-2.45

 ajusta

-2.45

POSITIVE LOGITS

棪

3.22

妡

3.03

厹

3.00

();

2.92

琑

2.59

豋

2.58

your

2.48

It

2.47

趼

2.41

2.39

Activations Density 0.003%