INDEX

Explanations

copyright notices

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

and

-1.75

 från

-1.23

 afbeeldingen

-1.20

Ưu

-1.20

ingin

-1.20

 goederen

-1.19

konstruktion

-1.19

--;

-1.18

 gegevens

-1.17

 wijze

-1.15

POSITIVE LOGITS

Nasc

1.25

¹.

1.24

<0xA3>

1.18

などを

1.17

سياسي

1.16

Hermoso

1.15

便利です

1.14

しかし

1.13

.¹

1.13

 conseguenze

1.12

Activations Density 0.057%