INDEX

Explanations

as [adjective/adverb] as possible

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

1.23

ﻦ

1.20

哪些

1.16

 многое

1.15

größe

1.12

𝗲

1.12

 fazla

1.11

’.”

1.11

ensburg

1.10

дцать

1.07

POSITIVE LOGITS

ے

1.52

ف

1.41

И

1.24

 Manohar

1.23

ڈین

1.23

쐞

1.22

Ли

1.21

 aortic

1.18

Ло

1.17

 inaccuracy

1.17

Activations Density 0.145%