INDEX

Explanations

consumer-facing apps

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

 certaines

-1.14

 Sofía

-1.13

 kalem

-1.11

obatan

-1.10

 cabaña

-1.09

textt

-1.07

 inability

-1.06

and

-1.06

 kulak

-1.06

<bos>

-1.05

POSITIVE LOGITS

corrhi

1.34

ocardial

1.34

>|</

1.32

͞

1.27

 regeringen

1.26

 azonban

1.23

hlten

1.21

itaji

1.17

áklad

1.17

You

1.17

Activations Density 0.365%