INDEX

Explanations

data after prepositions

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

 something

0.40

什么

0.38

something

0.38

อะไร

0.37

 Something

0.36

东西

0.36

 چیزی

0.35

 someth

0.35

 прият

0.35

뭔

0.35

POSITIVE LOGITS

 ingested

0.52

 newly

0.51

 freshly

0.50

 extracted

0.49

 harvested

0.48

 incoming

0.46

 specified

0.46

 selected

0.44

 randomly

0.44

 unlabeled

0.43

Activations Density 0.052%