INDEX

Explanations

code formatting and inclusions

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

to

-1.28

our

-1.21

or

-1.15

😛

-1.13

ctober

-1.09

gure

-1.08

NameExpr

-1.06

 from

-1.05

not

-1.03

….

-1.03

POSITIVE LOGITS

 préférence

1.25

KFC

1.18

 portavoz

1.17

 cheminée

1.13

donde

1.13

 légumes

1.13

絝

1.09

螻

1.09

 撮っ

1.08

SONY

1.08

Activations Density 0.001%