INDEX

Explanations

No Explanations Found

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

 Fuller

-0.10

oni

-0.09

elen

-0.09

rise

-0.08

lify

-0.08

/repository

-0.08

/entities

-0.08

uri

-0.08

 Jordan

-0.08

extr

-0.08

POSITIVE LOGITS

 Kron

0.10

zers

0.09

 class

0.08

asar

0.08

 deep

0.08

Gam

0.08

isque

0.08

 Sunshine

0.08

unner

0.08

 split

0.08

Activations Density 0.000%

No Known Activations