INDEX

Explanations

references to indexing and indexing-related terminology

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

du

-0.49

 saites

-0.45

 stab

-0.45

Jar

-0.45

ev

-0.44

тан

-0.43

Ent

-0.42

index

-0.42

 boundary

-0.42

du

-0.42

POSITIVE LOGITS

 indexed

3.41

indexed

2.88

 Indexed

2.63

Indexed

2.45

 indexing

1.91

 Indexing

1.80

indexing

1.70

Indexing

1.61

 فريبيس

0.89

 يتيمه

0.88

Activations Density 0.001%