INDEX

Explanations

leave/stay

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

 leave

-1.00

 Leave

-0.89

Leave

-0.85

 stay

-0.84

leave

-0.81

 Stay

-0.77

 LEAVE

-0.76

Stay

-0.69

stay

-0.58

 STAY

-0.58

POSITIVE LOGITS

orated

0.58

ridgeshire

0.57

 imageNamed

0.57

 Мексичка

0.56

 consulté

0.56

Trichloroethane

0.56

 imprisoned

0.56

qvarna

0.56

NOPQRST

0.56

KommentareTeilen

0.55

Activations Density 0.037%