INDEX

Explanations

No Explanations Found

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

 typename

-0.63

drawing

-0.59

 Robot

-0.58

 toegang

-0.55

 connaissent

-0.54

ssysteme

-0.54

 Drawing

-0.54

 drawings

-0.53

 Protocols

-0.52

 robots

-0.52

POSITIVE LOGITS

 fill

0.62

featureID

0.59

 power

0.58

randrange

0.54

tanleria

0.54

 propOrder

0.52

sop

0.51

WireFormat

0.47

jsdelivr

0.47

Fill

0.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.