INDEX

Explanations

learning resources and courses

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

Recovery

0.44

 Oahu

0.40

茵

0.39

Wire

0.39

 Ferro

0.39

฀

0.38

agascar

0.38

الو

0.38

assapi

0.37

복

0.37

POSITIVE LOGITS

 hugging

0.70

Hug

0.64

Sebastian

0.61

 Sebastian

0.59

 Weights

0.59

 weights

0.56

Kag

0.55

 blog

0.54

Weights

0.54

 illustrated

0.53

Activations Density 0.030%