INDEX

Explanations

instances of hearsay, indicated by words like "heard", "said", and "reviews".

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

No Comments

Negative Logits

 AssemblyCulture

-0.71

tagHelperRunner

-0.66

 propOrder

-0.64

 esternos

-0.60

inescent

-0.59

InjectAttribute

-0.57

IonicModule

-0.56

setVerticalGroup

-0.55

fromCharCode

-0.54

 CURIAM

-0.54

POSITIVE LOGITS

 rumored

0.66

 reputed

0.57

Batis

0.52

 rhestr

0.51

 appel

0.50

听说

0.49

 rumor

0.49

rze

0.48

 allegedly

0.48

migrationBuilder

0.48

Activations Density 0.055%