INDEX

Explanations

titles and section headers

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

可惜

-1.41

 instead

-1.33

 ciertos

-1.32

 residing

-1.26

 eenvou

-1.25

 rather

-1.24

ternut

-1.22

<h2>

-1.21

据说

-1.20

 dodatkowe

-1.20

POSITIVE LOGITS

蕪

1.35

 Championnat

1.30

л

1.21

êmios

1.19

 tertawa

1.19

носить

1.17

 اقتصادی

1.17

 نکن

1.16

々な

1.16

 Ministero

1.16

Activations Density 0.074%