INDEX

Explanations

references to navigation or guidance concepts

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

clair

-0.09

è®¾æĸ½

-0.07

 KeyCode

-0.07

ÏĢÎ¿Î½

-0.07

baugh

-0.07

ãĥ

-0.07

athe

-0.07

Ð¢Ð°

-0.07

atron

-0.07

ousse

-0.07

POSITIVE LOGITS

 breadcrumb

0.10

 breadcrumbs

0.09

breadcrumb

0.09

breadcrumbs

0.09

 bread

0.08

 Bread

0.08

Breadcrumb

0.07

iego

0.07

 links

0.07

 path

0.06

Activations Density 0.001%