INDEX

Explanations

legal, descriptive, or technical terms

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

 bezahlt

-1.27

 roślin

-1.25

 kaos

-1.22

⫹

-1.19

 teka

-1.19

𝐇

-1.18

 terap

-1.17

fehler

-1.17

 ВЫ

-1.16

𝐉

-1.16

POSITIVE LOGITS

of

1.45

暧

1.35

 burung

1.28

🪛

1.25

 wright

1.24

 kwenye

1.23

ּוֹ

1.20

гают

1.15

𝐳

1.14

С

1.13

Activations Density 0.010%