INDEX

Explanations

nonspecific quantities

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vidite

-0.81

 initComponents

-0.71

 genoux

-0.69

AnchorStyles

-0.68

 publiques

-0.67

 démocr

-0.66

 Audiodateien

-0.66

 extérieures

-0.66

 soigneusement

-0.66

 vaisseaux

-0.66

POSITIVE LOGITS

 some

1.23

0.82

some

0.78

any

0.75

few

0.65

 something

0.63

its

0.60

Some

0.59

an

0.57

 certain

0.54

Activations Density 0.000%