INDEX

Explanations

a followed by a new/strange/persistent feeling

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 [&](

1.73

Hepinize

1.73

UserRootDir

1.72

 Huyền

1.71

𒀯

1.69

Смалянчук

1.67

ㅂ

1.67

 vực

1.65

 Pusenkoff

1.65

𒊒

1.65

POSITIVE LOGITS

It

2.29

it

2.04

This

2.03

It

1.97

The

1.82

is

1.76

 This

1.70

 this

1.69

And

1.62

There

1.61

Activations Density 0.239%