INDEX

Explanations

words for lists

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

 impediments

0.56

 plumbers

0.54

 dampen

0.52

 pennies

0.50

 disappointments

0.48

 conduits

0.46

ammam

0.45

 axles

0.44

 turnips

0.43

 margarine

0.43

POSITIVE LOGITS

0.53

下一步

0.47

 Treaty

0.46

 restorative

0.45

 Leistungs

0.45

 Startup

0.45

Key

0.44

Ich

0.43

이

0.43

Vý

0.42

Activations Density 0.003%