INDEX

Explanations

given

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

 conmigo

-0.47

 sfor

-0.44

 répondu

-0.41

for

-0.40

 confirmé

-0.39

 CURIAM

-0.38

 conservé

-0.37

 immagin

-0.36

for

-0.36

oter

-0.36

POSITIVE LOGITS

 utafitiHapana

0.86

 autorytatywna

0.74

his

0.73

 ivelany

0.73

 Polsek

0.70

the

0.69

Попис

0.66

zzleHttp

0.66

بوابة

0.65

riculum

0.65

Activations Density 0.023%