INDEX

Explanations

Versions and revisions

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

uben

-0.30

IFO

-0.29

CEF

-0.27

ç»ĦæĪĲ

-0.25

caffe

-0.25

vvm

-0.25

itre

-0.25

ift

-0.24

Fen

-0.23

ç¼ĵ

-0.23

POSITIVE LOGITS

èµį

0.29

åĭģ

0.28

åĨ³è®®

0.25

//{{

0.25

rection

0.25

.blog

0.25

.ed

0.24

å£ħ

0.24

å¿ĥæĢĿ

0.24

Ð±Ð¸Ð½

0.24

Activations Density 0.031%