INDEX

Explanations

code snippets and URLs

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

 Hatter

-0.73

 होते

-0.73

 prefrontal

-0.72

 meringue

-0.71

 Belize

-0.68

ükü

-0.68

 CREAM

-0.68

urazione

-0.68

 viszont

-0.68

経歴

-0.68

POSITIVE LOGITS

chery

0.94

 adop

0.91

agerie

0.87

 höl

0.86

joined

0.85

 prints

0.85

plots

0.84

Nhan

0.81

ToString

0.81

Contours

0.79

Activations Density 0.002%