INDEX

Explanations

watch

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 watch

-1.40

watch

-1.33

 Watch

-1.25

Watch

-1.24

 WATCH

-1.12

WATCH

-0.98

 watched

-0.95

 watches

-0.94

 watching

-0.88

watches

-0.85

POSITIVE LOGITS

UrlResolution

0.77

InSection

0.74

BufferException

0.69

GOTREF

0.68

HasIndex

0.64

UnsafeEnabled

0.64

 mxArray

0.63

hasMoreElements

0.62

BeginContext

0.61

ResponseWriter

0.61

Activations Density 0.045%