INDEX

Explanations

Code, technical texts

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

pressed

-0.30

éĥ¯

-0.28

_vue

-0.27

æĭ¨

-0.26

 Ø§ÙĦØŃÙĤ

-0.25

èµĦæºĲ

-0.25

 ViewData

-0.25

 selection

-0.25

 Squad

-0.25

.toArray

-0.24

POSITIVE LOGITS

olon

0.33

ollo

0.31

ocol

0.27

cko

0.26

oint

0.26

 constitutional

0.25

amil

0.24

æįĲçĮ®

0.24

 core

0.24

coln

0.24

Activations Density 0.885%