INDEX

Explanations

auxiliary verbs and related words or punctuation

work

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

 working

-2.22

Working

-2.09

 Working

-2.05

working

-2.02

 WORKING

-1.93

WORKING

-1.78

Worked

-1.13

 Worked

-1.12

 worked

-1.10

 trabajando

-0.96

POSITIVE LOGITS

 work

1.22

 Work

0.83

work

0.82

Work

0.78

EndProject

0.72

DrawerToggle

0.69

 WORK

0.69

 незавершена

0.65

 obra

0.63

 werk

0.63

Activations Density 4.482%