INDEX

Explanations

Code and legal documents

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

flate

-0.31

ç»Ļèĩªå·±

-0.28

è¿¹

-0.28

erness

-0.27

[]*

-0.26

bish

-0.26

éģĹ

-0.26

uels

-0.25

 FName

-0.24

åı¯è§ģ

-0.24

POSITIVE LOGITS

 Spinner

0.29

 paragraph

0.27

pac

0.26

 article

0.26

rio

0.25

çļĦæĸĩç«ł

0.25

'article

0.25

 spinner

0.25

éļĶéŁ³

0.24

 Paragraph

0.24

Activations Density 0.001%