INDEX

Explanations

This followed by a verb or 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

1.78

an

1.54

า

1.53

1.48

ా

1.46

ご

1.40

ières

1.40

kih

1.34

 вопроса

1.33

eux

1.32

POSITIVE LOGITS

StructOf

1.45

 även

1.42

sembled

1.39

ست

1.38

 также

1.37

)}+

1.37

біць

1.36

,\,\,\,\

1.35

ement

1.32

ور

1.32

Activations Density 0.234%