INDEX

Explanations

code comments and 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

rolet

0.41

 theological

0.38

 شیخ

0.37

 defense

0.36

 assertive

0.36

లె

0.36

may

0.36

 intellectual

0.36

 Marco

0.36

 waterfront

0.36

POSITIVE LOGITS

 для

0.44

 για

0.44

dla

0.42

для

0.40

➘

0.39

 لاءِ

0.39

សម្រាប់ការ

0.38

^*_{

0.38

/<%=

0.38

Cuánto

0.38

Activations Density 0.025%