INDEX

Explanations

notes and academic concepts

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

 Schae

0.63

 haar

0.61

 tör

0.57

 timetable

0.57

 methodology

0.55

 Methodology

0.53

éticas

0.53

brat

0.51

율

0.50

 prohl

0.50

POSITIVE LOGITS

 Cornell

1.62

Cornell

1.55

note

1.50

 Note

1.45

notas

1.43

Brown

1.42

 note

1.41

 Brown

1.40

Note

1.39

You

1.38

Activations Density 0.414%