INDEX

Explanations

normal or ordinary concepts

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

 extremo

0.42

极其

0.41

 অদ্ভুত

0.39

 vantagem

0.37

 deux

0.36

 Expenditures

0.36

 extrêmement

0.36

 Très

0.36

䡊

0.35

 Tarifleri

0.34

POSITIVE LOGITS

普通の

1.47

通常の

1.36

 normal

1.34

 일반

1.30

 ordinary

1.25

 обычной

1.23

普通的

1.23

 normale

1.22

 обы

1.20

普通

1.20

Activations Density 0.707%