INDEX

Explanations

numeric codes and references typically associated with academic citations or identifiers

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

 é¢¨

-0.07

cess

-0.06

Å¡Å¥

-0.06

porno

-0.06

èī¦

-0.06

spam

-0.06

dum

-0.06

isches

-0.06

umper

-0.06

qi

-0.06

POSITIVE LOGITS

cente

0.07

ussen

0.07

ì§ĢëıĦ

0.07

aroo

0.07

åĨ

0.06

 Carpenter

0.06

PELL

0.06

feit

0.06

PUTE

0.06

uct

0.06

Activations Density 0.004%