INDEX

Explanations

{{

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

antMatchers

-0.56

:+:

-0.54

lccn

-0.54

 boto

-0.51

UniformLocation

-0.50

 préfé

-0.48

 ویکی‌پدیای

-0.48

 GenerationType

-0.48

assung

-0.47

 فريبيس

-0.47

POSITIVE LOGITS

 pretty

0.63

pretty

0.55

 PRET

0.54

 الاطلاع

0.50

 propOrder

0.48

FOOTNOTES

0.47

paž

0.46

Looper

0.46

addLast

0.46

czuk

0.46

Activations Density 0.058%