INDEX

Explanations

proper nouns and punctuation

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

if

-1.45

 ondas

-1.45

 their

-1.42

 which

-1.38

at

-1.34

-1.23

 promote

-1.23

سبة

-1.16

 when

-1.16

 just

-1.13

POSITIVE LOGITS

()">

1.13

1.07

</em>

1.05

 xxiv

1.05

 dunque

1.04

 magnificent

1.04

 horrid

1.04

different

1.02

 xxii

1.02

during

1.02

Activations Density 0.001%