INDEX

Explanations

code and/or poetry, syntax

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

itter

-0.29

fed

-0.27

åĽŀåĪ°

-0.26

éĶı

-0.26

rique

-0.26

artz

-0.25

 broadcast

-0.25

 âĢ¦

-0.24

ãĤ¢ãĤ¯ãĤ»ãĤ¹

-0.24

 Ð»Ð¸

-0.24

POSITIVE LOGITS

 </>↵

0.29

:''

0.28

ä½Ĩä»į

0.28

apus

0.27

æĥłæ°ĳ

0.27

ignon

0.26

ä¸įåģľ

0.25

//}↵

0.25

@endforeach

0.25

Untitled

0.25

Activations Density 0.003%