INDEX

Explanations

Technical documentation snippets

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

 kasarigan

-0.65

 CreateTagHelper

-0.60

 HomeComponent

-0.60

 صوتيه

-0.58

 Roskov

-0.56

orsese

-0.54

elerik

-0.53

 NCERT

-0.52

 inalámbrico

-0.52

WriteTagHelper

-0.52

POSITIVE LOGITS

 Dining

0.50

 Auxiliary

0.50

 Physical

0.48

 Capital

0.47

 grounds

0.47

 capital

0.47

mals

0.47

 Real

0.46

 dining

0.46

 Grounds

0.45

Activations Density 0.003%