INDEX

Explanations

the word "Edition" appearing in text

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

</i>

-0.60

Gustav

-0.58

انيف

-0.57

 gras

-0.57

lographic

-0.55

ICR

-0.55

Na

-0.54

 Gras

-0.54

Ar

-0.54

❷

-0.54

POSITIVE LOGITS

 edition

1.31

edition

1.31

 Edition

1.30

 editions

1.25

Edition

1.18

 EDITION

1.11

 pleaſure

0.98

 Editions

0.95

 purpoſe

0.94

 Untold

0.90

Activations Density 0.007%