INDEX

Explanations

making recipes or terrible brews

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

 Moritz

0.74

Aden

0.70

 Aden

0.69

 DeConcini

0.67

 Zebra

0.64

 rollup

0.64

 sand

0.63

 Gibraltar

0.63

 buffer

0.63

 প্রস

0.61

POSITIVE LOGITS

 cooking

2.40

 Cooking

2.31

Cooking

2.23

 cook

2.20

 kitchen

2.14

 cooks

2.14

cooking

2.11

Cook

2.11

 Cook

2.08

 kitchens

1.98

Activations Density 0.765%