INDEX

Explanations

Web addresses and code

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

">//

-0.62

</thead>

-0.60

 Bourgoin

-0.59

 AssemblyCompany

-0.56

HtmlAttribute

-0.54

)}</

-0.54

Santis

-0.53

 '\\;'

-0.51

rizona

-0.50

oncé

-0.49

POSITIVE LOGITS

 trick

0.76

 pouring

0.65

 flowing

0.60

 flooding

0.59

GenerationType

0.57

 Trick

0.56

trick

0.56

 trickle

0.55

Trick

0.53

yntaxException

0.53

Activations Density 0.000%