INDEX

Explanations

is

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

ç¿ķ

-0.27

jee

-0.26

 Feather

-0.25

æ³¡æ³¡

-0.25

ebb

-0.25

çĬ¹è±«

-0.25

 prag

-0.24

chester

-0.24

ç»ĨåĪĻ

-0.24

 intuit

-0.23

POSITIVE LOGITS

 story

0.45

story

0.43

 stories

0.42

æķħäºĭ

0.41

è®°å½ķ

0.40

 record

0.39

 tell

0.39

è®²è¿°

0.36

 tales

0.36

 learn

0.36

Activations Density 0.882%