INDEX

Explanations

norms and standards

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

 Dinas

-1.42

 alcune

-1.24

 horrid

-1.23

 magnific

-1.20

actually

-1.19

 allerlei

-1.17

 betreffende

-1.16

perhaps

-1.13

 Herbs

-1.10

considered

-1.09

POSITIVE LOGITS

 ones

2.19

one

2.19

 because

1.75

 those

1.75

 despite

1.48

 providing

1.41

 after

1.41

 what

1.41

 placing

1.40

 before

1.38

Activations Density 0.071%