INDEX

Explanations

references to scientific attribution or attributional processes

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

principalColumn

-0.72

Rhestr

-0.68

HtmlAttribute

-0.68

 ErrIntOverflow

-0.62

TProtocol

-0.60

 للمعارف

-0.59

 <>",

-0.59

 copro

-0.58

MessageOf

-0.58

 semif

-0.58

POSITIVE LOGITS

 attributed

2.55

 ascribed

1.67

attributed

1.64

 atribu

1.16

 attribution

1.16

 attribué

1.11

 attributable

1.09

Attributed

1.01

 attribu

0.96

 ascribe

0.81

Activations Density 0.003%