INDEX

Explanations

Hong

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

Hong

-0.86

 Hong

-0.80

 hong

-0.65

InstrumentedTest

-0.65

 Directorate

-0.64

hong

-0.63

NameInMap

-0.54

 ProtoMessage

-0.52

 Autorisations

-0.50

Cyfeiriadau

-0.49

POSITIVE LOGITS

ViewFeatures

0.79

ongiorno

0.62

anguages

0.61

 rapides

0.58

 Turquie

0.57

actionMode

0.57

gridx

0.54

GZIP

0.54

strix

0.53

󠁢

0.53

Activations Density 0.006%