INDEX

Explanations

capitalized words or phrases that might be titles or character names

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Huf

-0.47

 police

-0.44

υ

-0.43

NOPQRST

-0.42

 artigo

-0.42

eig

-0.42

iomanip

-0.41

Mutagenicity

-0.41

IEN

-0.41

POSITIVE LOGITS

 Thrones

1.34

enerys

1.16

 للاسماء

0.85

 Dany

0.84

aryen

0.77

Tembelea

0.76

HBO

0.73

AndEndTag

0.73

HBO

0.72

 Quentin

0.69

Activations Density 0.012%