INDEX

Explanations

mathematical symbols and characters associated with mathematical equations or expressions

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

 Samurai

-0.08

Elk

-0.07

_ELEM

-0.07

 Einstein

-0.07

Zen

-0.07

 Sikh

-0.07

Nik

-0.07

 Honolulu

-0.06

SPORT

-0.06

Bik

-0.06

POSITIVE LOGITS

 Flowers

0.13

 Flower

0.10

 Doll

0.10

 Virginia

0.10

Virginia

0.09

 flower

0.09

 Andrews

0.09

 dolls

0.09

 incest

0.09

 Cathy

0.08

Activations Density 0.004%