INDEX

Explanations

At

describing concepts and entities

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

vä

0.52

cac

0.49

кторов

0.48

вав

0.46

瑣

0.44

욀

0.44

nader

0.43

ног

0.43

чення

0.42

pkey

0.42

POSITIVE LOGITS

 atelier

0.51

 Atlético

0.48

 Atelier

0.48

 大人

0.47

 اتاق

0.47

 metabol

0.46

 Module

0.46

 molyb

0.46

 Atkins

0.45

 materially

0.45

Activations Density 0.002%