INDEX

Explanations

descriptive words related to movement and direction

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

apult

-0.08

 ØŃÙħÙĦ

-0.08

ouz

-0.07

ÐºÐ°Ñģ

-0.07

íĢ

-0.07

LEGRO

-0.07

.Interop

-0.07

ÑĤÐ°Ð¶

-0.07

ousel

-0.07

 mÃŃn

-0.07

POSITIVE LOGITS

0.08

ery

0.07

lic

0.07

thal

0.06

aden

0.06

 fora

0.06

Fu

0.06

 Kron

0.06

ibar

0.06

0.05

Activations Density 0.009%