INDEX

Explanations

// or # followed by keywords

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

 любые

0.44

 избе

0.42

 errors

0.40

 avoided

0.40

/).

0.40

etal

0.39

অব

0.39

)}-

0.38

仮

0.38

trivial

0.38

POSITIVE LOGITS

 Means

0.54

 means

0.52

Means

0.52

 someone

0.48

 znamená

0.48

 berarti

0.48

Someone

0.47

 Found

0.47

someone

0.46

 somebody

0.46

Activations Density 0.028%