INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ethics

0.69

practical

0.66

candidate

0.64

Ю

0.64

scaling

0.63

ع

0.63

winner

0.63

boiler

0.61

Что

0.60

releases

0.60

POSITIVE LOGITS

滕

0.70

 Yolanda

0.66

т

0.66

 Scooter

0.63

 מפ

0.61

 Scrub

0.61

 Loren

0.61

тен

0.61

TAB

0.60

 Lindsey

0.60

Activations Density 0.000%

No Known Activations