INDEX

Explanations

joke, sentiment, chart

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lou

-0.10

 dart

-0.09

inho

-0.09

Omn

-0.09

ÙĪØ¨ÛĮ

-0.09

ment

-0.09

 loung

-0.09

omn

-0.09

fk

-0.09

 Leah

-0.08

POSITIVE LOGITS

createView

0.10

:č\nč\n

0.09

ï¾Ĭ

0.09

Drv

0.08

herits

0.08

 slim

0.08

 '');\n\n

0.08

nodoc

0.08

/proto

0.08

 ofType

0.08

Activations Density 0.012%