INDEX

Explanations

references to specific measurements or sizes

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

ago

-0.08

stal

-0.06

orro

-0.06

estion

-0.06

 anim

-0.06

 animate

-0.06

erties

-0.06

st

-0.06

ÑĢÑĥÐ½

-0.06

 spin

-0.05

POSITIVE LOGITS

-paper

0.10

Paper

0.09

 paper

0.09

 Paper

0.08

 papel

0.08

_paper

0.08

ãĤµãĤ¤ãĤº

0.08

çº¸

0.08

 dimensions

0.08

ç´Ļ

0.08

Activations Density 0.011%