INDEX

Explanations

code structure and punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ød

-1.28

by

-1.27

 اگر

-1.26

 Paglinawan

-1.22

通过

-1.22

immt

-1.21

 zrobić

-1.20

 если

-1.18

коном

-1.17

 скриншот

-1.16

POSITIVE LOGITS

 also

2.25

 this

1.79

his

1.69

1.66

its

1.46

1.45

 then

1.41

 these

1.41

1.38

1.36

Activations Density 0.012%