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

urgeon

-0.28

 inspected

-0.28

Grow

-0.27

 paced

-0.26

owned

-0.24

è£¸

-0.24

 Grow

-0.24

 Peach

-0.23

èĤ²

-0.23

 wholesome

-0.23

POSITIVE LOGITS

 Bender

0.30

aÃ§Ã£o

0.27

å¾Ļ

0.26

aÃ§Ãµes

0.26

Ð¸Ð·Ð°ÑĤÐ¾ÑĢ

0.25

onso

0.25

ost

0.24

Ñŀ

0.24

åĢ¼

0.24

è¯´æĺİ

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.