INDEX

Explanations

author followed by a descriptor

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

 чему

1.45

 कहा

1.35

 организма

1.32

сць

1.32

om

1.32

 ধরনের

1.30

 बहुमत

1.28

1.27

گاه

1.27

 envolvendo

1.26

POSITIVE LOGITS

बेट

1.24

Thank

1.22

nment

1.20

ये

1.18

籍

1.16

ות

1.15

non

1.14

嘞

1.12

مط

1.11

 جعلی

1.10

Activations Density 0.013%