INDEX

Explanations

of

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ligiloj

-0.54

före

-0.47

förs

-0.46

ről

-0.45

licité

-0.45

väg

-0.40

—

-0.39

BagConstraints

-0.39

 connexes

-0.39

KeyStore

-0.38

POSITIVE LOGITS

 myſelf

1.13

 Monfieur

1.09

 Majefty

1.02

 itſelf

0.99

 purpoſe

0.98

 himſelf

0.94

 Diſ

0.94

Efq

0.93

 themſelves

0.92

 theſe

0.92

Activations Density 0.054%