INDEX

Explanations

stroke

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

Efq

-0.89

 myſelf

-0.75

<bos>

-0.73

 ſeveral

-0.73

mặt

-0.71

 itſelf

-0.69

 Monfieur

-0.68

 raiſ

-0.67

 Chriftian

-0.66

 theſe

-0.66

POSITIVE LOGITS

Gön

0.59

 gawas

0.54

 aeruginosa

0.53

 pylori

0.52

Portail

0.50

queryInterface

0.49

 Clear

0.46

az

0.45

alité

0.45

Activations Density 0.133%