INDEX

Explanations

code structure and data fields

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

mitted

1.45

্লিক

1.40

್

1.35

ت

1.34

ుడు

1.31

_,

1.30

ebab

1.27

wych

1.26

绎

1.22

POSITIVE LOGITS

ık

1.55

<bos>

1.36

❛

1.24

nungen

1.24

ạ

1.23

ра

1.22

 malade

1.22

 formé

1.22

습니다

1.22

 сприя

1.20

Activations Density 0.227%