INDEX

Explanations

code examples

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 heutigen

-0.06

 dong

-0.06

江南

-0.06

 invece

-0.06

껏

-0.06

 Straße

-0.06

 Ecology

-0.06

 ενός

-0.06

 sólo

-0.06

 media

-0.06

POSITIVE LOGITS

RIG

0.06

оти

0.06

 exemplo

0.06

!!

0.06

 contoh

0.06

Honda

0.06

 ወቅት

0.05

EmbeddedResource

0.05

 এবার

0.05

 ejemplo

0.05

Activations Density 0.015%