INDEX

Explanations

references to mathematical concepts and properties

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

vastava

-0.68

 Chriſt

-0.66

ższe

-0.60

 myſelf

-0.60

 neceſſ

-0.59

 Monfieur

-0.57

ContentLoaded

-0.57

 lèvres

-0.57

 whoſe

-0.56

StoryboardSegue

-0.56

POSITIVE LOGITS

ł

3.58

Ł

2.16

ła

2.02

ło

1.75

ły

1.59

łem

1.26

Ł

1.23

ł

1.18

łowa

1.09

łami

1.07

Activations Density 0.001%