INDEX

Explanations

No Explanations Found

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

ÑĥÐ¼Ð¾Ð²

-0.08

amac

-0.08

iku

-0.07

Ú©Ø´

-0.07

ftar

-0.07

arten

-0.07

_sqrt

-0.07

.metamodel

-0.07

lexport

-0.07

ÙĤØ§Øª

-0.07

POSITIVE LOGITS

oola

0.07

0.06

pard

0.06

 essentially

0.06

it

0.06

undi

0.06

.ad

0.06

 Erect

0.06

 basically

0.05

Adv

0.05

Activations Density 0.000%

No Known Activations

This feature has no known activations.