INDEX

Explanations

how and why things are used

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

Annex

0.39

pt

0.37

 vertrou

0.37

ект

0.37

 Annex

0.37

 stronger

0.36

 retrieving

0.35

체를

0.35

IRED

0.35

ić

0.35

POSITIVE LOGITS

 warum

0.46

 условия

0.40

USAGE

0.40

 термин

0.39

usage

0.39

使い方

0.39

 waarom

0.38

why

0.38

how

0.38

 وضعیت

0.38

Activations Density 0.001%