INDEX

Explanations

medicine

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

 Paglinawan

-0.69

 varandra

-0.66

ergies

-0.65

 myſelf

-0.64

umumkan

-0.64

WRP

-0.64

 Torr

-0.63

ộn

-0.63

Arp

-0.63

 houſe

-0.62

POSITIVE LOGITS

 Zweig

0.44

 AssemblyTitle

0.41

az

0.40

cu

0.40

 CreateTagHelper

0.40

นิ

0.39

Cubit

0.39

vit

0.38

AutoScale

0.38

DataPropertyName

0.38

Activations Density 0.037%