INDEX

Explanations

Statistics and reports

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

åı«æĪĳ

-0.28

Swe

-0.27

alse

-0.25

åĲĦè¡Į

-0.25

à¹Ĥà¸ļà¸£à¸²à¸ĵ

-0.24

happy

-0.24

ugal

-0.24

vez

-0.24

 XCTAssertTrue

-0.24

agrid

-0.24

POSITIVE LOGITS

ric

0.31

rics

0.30

lic

0.29

eness

0.28

é¨

0.27

ie

0.27

tra

0.27

oul

0.27

ä¸ĢåŃ£åº¦

0.27

Activations Density 0.004%