INDEX

Explanations

references to user instructions or actions

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

arp

-0.07

apl

-0.07

brero

-0.06

 ÑģÐ¾Ð±Ð¾Ñİ

-0.06

á»¡

-0.06

Ð²Ð¸

-0.06

ivi

-0.06

engl

-0.06

planes

-0.06

POSITIVE LOGITS

 must

0.09

may

0.08

 will

0.08

Must

0.07

 Must

0.07

Tokenizer

0.06

will

0.06

 should

0.06

may

0.06

must

0.06

Activations Density 0.023%