INDEX

Explanations

@ followed by author, link, copyright, or package

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

↵

-0.09

@↵

-0.09

bih

-0.08

+↵

-0.08

↵

-0.08

saf

-0.08

sdale

-0.08

ika

-0.08

 fate

-0.08

''↵

-0.08

POSITIVE LOGITS

agina

0.09

mop

0.09

lus

0.09

Vac

0.08

 Tech

0.08

 outr

0.08

eds

0.08

ifice

0.08

--------------

0.08

 regs

0.08

Activations Density 0.160%