INDEX

Explanations

category or topic labels in a document

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

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

-0.08

antry

-0.08

ÐµÐ»Ð¸Ñĩ

-0.07

elez

-0.07

ÑĤÑĢÐ¾

-0.07

eson

-0.07

:focus

-0.07

odel

-0.07

illo

-0.07

ullo

-0.07

POSITIVE LOGITS

amaz

0.06

 destac

0.06

Ã¤s

0.06

 abuse

0.05

ati

0.05

 harm

0.05

orang

0.05

 impress

0.05

ajor

0.05

Alb

0.05

Activations Density 0.007%