INDEX

Explanations

star

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 star

-1.71

 Star

-1.63

star

-1.49

Star

-1.32

 STAR

-1.02

 California

-0.89

星

-0.89

STAR

-0.85

 स्टार

-0.84

 estrella

-0.79

POSITIVE LOGITS

 itſelf

1.44

 myſelf

1.38

Efq

1.27

 Majefty

1.23

 Theſe

1.22

 themſelves

1.17

 Jefus

1.16

 Reſ

1.13

 Monfieur

1.13

 ſeveral

1.12

Activations Density 0.864%