INDEX

Explanations

paths and series titles

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

潆

-1.48

↵

-1.40

-1.37

 некоторых

-1.32

 style

-1.22

 большую

-1.20

 after

-1.19

 method

-1.15

 spacious

-1.15

 після

-1.13

POSITIVE LOGITS

ɗ

1.41

 vieta

1.40

 būt

1.36

parently

1.35

 '../../../../

1.25

 ſont

1.22

 così

1.21

 others

1.21

 They

1.20

佧

1.20

Activations Density 0.060%