INDEX

Explanations

you and yourself

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 notorious

-0.31

 massive

-0.31

 famous

-0.30

èİ«åĲįåħ¶

-0.30

å·¨é¢Ŀ

-0.30

å¤§çīĩ

-0.29

éĿŀå¸¸é«ĺ

-0.29

å·¨å¤§

-0.29

 infamous

-0.29

æĮ¦

-0.28

POSITIVE LOGITS

å°Ĭéĩį

0.33

 respectful

0.32

å¦¥åĸĦ

0.31

 yourself

0.30

-peer

0.29

åĴĮæĶ¯æĮģ

0.29

çľŁè¯ļ

0.29

incare

0.29

 thoughtful

0.28

èº«è¾¹

0.28

Activations Density 0.006%