INDEX

Explanations

proper nouns

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

MC

-0.70

MC

-0.69

 Matthew

-0.68

 Paul

-0.60

mc

-0.60

Matthew

-0.59

age

-0.55

paul

-0.52

 Michael

-0.52

Paul

-0.49

POSITIVE LOGITS

 ſeveral

1.16

 itſelf

1.16

 myſelf

1.16

Efq

1.14

 Monfieur

1.14

 StatefulWidget

1.13

 ſmall

1.10

 poffible

1.09

 purpoſe

1.09

 Jefus

1.08

Activations Density 0.468%