INDEX

Explanations

web content and code

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

 life

-0.29

.life

-0.27

 Life

-0.27

Life

-0.26

 bridge

-0.26

 Bridge

-0.25

-life

-0.25

fra

-0.25

çĶŁæ´»ä¸Ń

-0.24

çĶŁäº§çĶŁæ´»

-0.24

POSITIVE LOGITS

apist

0.31

æķĻä¼ļ

0.28

åģ¥

0.26

éĴľ

0.26

rom

0.26

ç¥·

0.25

å®ĹæķĻ

0.25

å§¿æĢģ

0.25

 bible

0.25

 arte

0.24

Activations Density 0.902%