INDEX

Explanations

references to grievance-related terminology or reports of grievance activities

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

HasAnnotation

-0.66

Sph

-0.59

dafx

-0.59

İstinadlar

-0.56

antd

-0.56

 tendenza

-0.56

FAP

-0.55

তথ্যসূত্র

-0.54

 OkHttpClient

-0.54

 يتيمه

-0.54

POSITIVE LOGITS

 grievance

3.53

 grievances

3.14

 Grie

2.33

grie

1.97

Grie

1.91

 aggrieved

1.25

 grie

0.91

 wronged

0.85

 hardship

0.74

 grudge

0.71

Activations Density 0.005%