INDEX

Explanations

symbols or characters from different languages or encoding formats

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

 Euros

-0.06

zon

-0.05

 Jord

-0.05

 answering

-0.05

Zone

-0.05

 Zone

-0.05

 Final

-0.05

 Vert

-0.05

 zone

-0.05

 ageing

-0.05

POSITIVE LOGITS

liquid

0.13

 liquid

0.12

Liquid

0.12

 Liquid

0.12

 scram

0.10

 liquids

0.10

 liqu

0.09

æ¶²

0.09

iquid

0.09

 unsigned

0.09

Activations Density 0.001%