INDEX

Explanations

Types of people

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 legislation

-0.27

automation

-0.27

çķ

-0.27

War

-0.26

 wife

-0.25

éħįéĢģ

-0.25

Nan

-0.24

Bot

-0.24

agger

-0.24

enÃ§Ã£o

-0.23

POSITIVE LOGITS

äº¤æį¢

0.27

GBT

0.27

éĢ¾æľŁ

0.26

åĬ¡

0.26

tent

0.25

 otherwise

0.25

ä¼ļéĢīæĭ©

0.25

everything

0.25

ä¸¤è¾¹

0.25

otherwise

0.25

Activations Density 0.006%