INDEX

Explanations

mixed language academic and code contexts

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

by

-1.97

and

-1.95

For

-1.72

 What

-1.68

Why

-1.66

-1.45

new

-1.44

How

-1.43

of

-1.42

for

-1.38

POSITIVE LOGITS

 rése

1.82

 prosjek

1.72

 immagini

1.67

 другой

1.66

 sokak

1.61

 stratég

1.60

its

1.59

.*")]

1.55

 trouva

1.55

 ferait

1.53

Activations Density 0.161%