INDEX

Explanations

references to articles, posts, stories, or reviews

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

chnitt

-0.07

ieder

-0.07

oris

-0.07

annel

-0.07

uml

-0.07

ableViewController

-0.07

ilar

-0.06

ypse

-0.06

iÄĻ

-0.06

POSITIVE LOGITS

ELLOW

0.07

 nackte

0.07

an

0.06

åľ³

0.06

 tick

0.06

gaard

0.06

ersen

0.06

upp

0.06

olib

0.06

uard

0.06

Activations Density 0.001%