INDEX

Explanations

peeling off protective layers

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

 pungkasnya

-0.69

 Navarro

-0.68

Lug

-0.67

 bahç

-0.66

_{+

-0.66

 dolayı

-0.65

 condiv

-0.64

 caja

-0.64

idenav

-0.64

bok

-0.63

POSITIVE LOGITS

 protective

2.36

 Protective

2.13

protective

2.06

Protective

1.99

 protecting

1.37

保護

1.33

 protectors

1.30

 защи

1.28

 backing

1.27

 sticker

1.26

Activations Density 0.031%