INDEX

Explanations

questions that challenge opinions or ideas

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

erland

-0.09

AYER

-0.07

atrix

-0.07

ocache

-0.06

lei

-0.06

arna

-0.06

 pragma

-0.06

Î²Î¿

-0.06

dma

-0.06

amburger

-0.06

POSITIVE LOGITS

 à¤ĩà¤¤à¤¨

0.08

Whenever

0.07

 bother

0.07

 whenever

0.07

 insists

0.06

ãģĵãĤĵãģª

0.06

CAPE

0.06

so

0.06

 tÃ£o

0.06

 Whenever

0.06

Activations Density 0.019%