INDEX

Explanations

retrieving information from sources

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

mathb

0.45

 Danh

0.44

voting

0.42

czyny

0.42

Jesse

0.41

 अनुभव

0.40

elij

0.40

 العنوان

0.40

 tytu

0.40

CLion

0.40

POSITIVE LOGITS

 recall

0.48

 artificial

0.47

 Recall

0.44

 propaganda

0.42

 erinn

0.42

 superficial

0.42

 indirect

0.41

 kilometers

0.40

 sedative

0.39

 memoria

0.38

Activations Density 0.016%