INDEX

Explanations

markup tags and structures

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

to

-1.70

and

-1.48

 that

-1.34

 Each

-1.34

 from

-1.28

an

-1.27

 after

-1.27

 With

-1.23

 Since

-1.23

 After

-1.22

POSITIVE LOGITS

 cúp

1.40

ALLENGES

1.29

苼

1.27

ATURA

1.22

 récents

1.20

 сына

1.19

粉丝

1.17



1.16

$\

1.15

 trasero

1.14

Activations Density 0.001%