INDEX

Explanations

friendly and inviting

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

 things

-1.36

一件

-1.29

 índice

-1.28

 importantes

-1.27

 یک

-1.23

罽

-1.22

 anderen

-1.20

-1.18

 Características

-1.16

哙

-1.16

POSITIVE LOGITS

=")

1.36

 Resmi

1.23

 Ramadhan

1.22

and

1.20

>--}}

1.18

<tr>

1.16

月は

1.16

 Karya

1.15

 fars

1.14

 Conci

1.13

Activations Density 0.031%