INDEX

Explanations

references to online platforms, social media, or internet-related user activity

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

File

-0.68

'{@

-0.62

хьтан

-0.61

 listeners

-0.60

SourceChecksum

-0.59

 readers

-0.59

 audiences

-0.58

 HasFactory

-0.58

 fans

-0.56

fans

-0.56

POSITIVE LOGITS

 users

0.75

 Users

0.71

iedz

0.66

وفاته

0.64

nein

0.61

 USERS

0.61

User

0.60

ádza

0.57

xase

0.57

 Usage

0.56

Activations Density 0.006%