INDEX

Explanations

numbers enclosed in parentheses

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

 falling

-0.85

Falling

-0.78

落地

-0.75

 Falling

-0.75

Apparatus

-0.74

 Deniz

-0.73

льне

-0.71

 liet

-0.71

ódź

-0.71

 fall

-0.71

POSITIVE LOGITS

манда

0.80

 licenci

0.79

 team

0.78

grey

0.73

⋆

0.73

 grey

0.72

brad

0.72

DYNAMIC

0.72

清水

0.71

 onlyOwner

0.71

Activations Density 0.030%