INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĭĻ

-0.28

 usual

-0.27

enet

-0.26

å¤®

-0.25

çº¬

-0.25

æİ¥åĪ°

-0.24

åĿĤ

-0.24

è¿ħ

-0.24

few

-0.23

)[:

-0.23

POSITIVE LOGITS

asmus

0.29

 promises

0.27

ä¸Ģä¸ĸ

0.26

 promise

0.25

ÑģÐµÐ½

0.24

ä¼ļè®©

0.24

ä¼ļç»Ļ

0.23

æ¾Ħæ¸ħ

0.23

 Alleg

0.23

ÑģÐ¾ÑĢ

0.23

Activations Density 0.028%

No Known Activations

This feature has no known activations.