INDEX

Explanations

phrases that emphasize the frequency or repetition of actions and events

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

ero

-0.07

ryn

-0.07

riel

-0.06

ilde

-0.06

ynthia

-0.06

adesh

-0.06

aug

-0.06

lu

-0.06

oras

-0.06

POSITIVE LOGITS

oeff

0.08

 Wilkinson

0.06

 prelim

0.06

"'

0.06

ault

0.06

eterangan

0.06

DM

0.06

 WebClient

0.06

Argb

0.06

ugas

0.06

Activations Density 0.015%