INDEX

Explanations

recreate environment or experiments

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

带着

0.40

潁

0.39

嶅

0.39

จะ

0.38

Ᏺ

0.38

ってきた

0.37

 fluidity

0.37

ToolStrip

0.37

зал

0.37

 cache

0.37

POSITIVE LOGITS

 United

0.44

 Theoretical

0.41

 Explain

0.41

Eg

0.40

 Contrary

0.40

même

0.39

 Это

0.39

 This

0.39

 Sweden

0.39

 colleagues

0.38

Activations Density 0.005%