INDEX

Explanations

positive experiences or statements

positive experiences

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

 Action

-0.75

fun

-0.75

 action

-0.74

Action

-0.68

fun

-0.66

 pleaſure

-0.66

action

-0.65

 becauſe

-0.64

Fun

-0.62

atimes

-0.62

POSITIVE LOGITS

 autorytatywna

0.63

Бахар

0.57

AxisAlignment

0.49

VIAF

0.46

XmlAccessType

0.46

ChildScrollView

0.45

deviantart

0.45

 jspb

0.44

 OnInit

0.44

ScopeManager

0.43

Activations Density 0.744%