INDEX

Explanations

references to people who have died

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

No Comments

Negative Logits

er

-0.62

 livet

-0.54

 life

-0.52

tel

-0.50

 بشر

-0.46

vij

-0.45

Nobody

-0.45

ath

-0.45

递

-0.45

</h3>

-0.44

POSITIVE LOGITS

 Deceased

1.15

 Roskov

1.04

 autorytatywna

1.02

 deceased

1.02

deceased

1.00

 незавершена

0.97

@"/

0.94

 linkovi

0.94

findpost

0.93

 kasarigan

0.93

Activations Density 0.009%