INDEX

Explanations

arithmetic expressions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ori

-0.06

 mixed

-0.06

 Gros

-0.06

"default

-0.06

iaux

-0.06

ESH

-0.06

 praying

-0.06

 chiefly

-0.06

 precision

-0.06

 gast

-0.06

POSITIVE LOGITS

fen

0.11

sanitize

0.10

|-

0.10

 branch

0.10

rov

0.10

ifact

0.10

 Languages

0.09

uni

0.09

 hunter

0.09

pen

0.09

Activations Density 0.068%