INDEX

Explanations

a variety of different conversational speech markers, including names, interjections, and discourse markers.

ton

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

 viewDidLoad

-0.46

 cielos

-0.42

 alta

-0.40

most

-0.37

Према

-0.37

תם

-0.37

 crecer

-0.37

OPO

-0.36

entrant

-0.36

çe

-0.36

POSITIVE LOGITS

ьаж

0.72

 >=",

0.71

 unknownFields

0.69

ItemBackground

0.66

 himo

0.66

 MainAxisSize

0.63

@"/

0.63

RTEE

0.63

atguigu

0.63

fjspx

0.63

Activations Density 1.539%