INDEX

Explanations

end of sentence punctuation

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

藜

-1.26

konos

-1.21

糖尿病

-1.21

Į

-1.14

The

-1.14

 saveurs

-1.12

⠀⠀

-1.11

 about

-1.09

 opzioni

-1.07

וּ

-1.07

POSITIVE LOGITS

and

1.73

my

1.21

 сахара

1.20

それを

1.16

 hope

1.09

ولوجيا

1.09

所で

1.05

imdi

1.04

 thank

1.03

みます

1.03

Activations Density 0.014%