INDEX

Explanations

mathematical notation or symbols related to optimization or parameters in equations

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

ÑĢÐ°Ð²Ð°

-0.07

vap

-0.07

gree

-0.07

chine

-0.06

 favoured

-0.06

 neighbouring

-0.06

oking

-0.06

Ves

-0.06

/fonts

-0.06

},'

-0.06

POSITIVE LOGITS

IRM

0.11

IR

0.09

 Manual

0.09

 Penalty

0.08

 manual

0.08

IRC

0.08

 Exhibit

0.07

Manual

0.07

IMS

0.07

 penalty

0.07

Activations Density 0.006%