INDEX

Explanations

HTML/XML-like tags and structure references

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

“

-0.08

 Â«

-0.07

 âĢŀ

-0.07

ToProps

-0.07

ëŀµ

-0.06

)<<

-0.06

 ãĢĮ

-0.06

 Clement

-0.06

oen

-0.06

¿Ĳ

-0.06

POSITIVE LOGITS

bsite

0.07

mare

0.07

ward

0.07

ahoma

0.07

crease

0.07

apons

0.07

ading

0.07

allee

0.07

ly

0.07

avery

0.06

Activations Density 0.041%