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

TH

-0.27

nÃ©

-0.27

jt

-0.27

<Any

-0.27

á»ĩp

-0.26

wright

-0.26

masÄ±

-0.25

å®ļéĩı

-0.24

åĵģ

-0.24

Fort

-0.24

POSITIVE LOGITS

eren

0.27

.Popen

0.27

 pans

0.26

coverage

0.26

 bibliography

0.26

 Covers

0.25

-cover

0.24

ä¸Ģç¾¤äºº

0.24

 Coverage

0.24

egen

0.24

Activations Density 0.008%

No Known Activations

This feature has no known activations.