INDEX

Explanations

references to amounts of time or duration

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 ModelExpression

-0.52

 MAYOR

-0.49

obal

-0.48

 mayor

-0.47

 Times

-0.47

EditPart

-0.47

 AppCompatTheme

-0.45

ÓS

-0.45

èr

-0.45

 race

-0.45

POSITIVE LOGITS

 themſelves

0.91

 myſelf

0.90

 raiſ

0.84

 himſelf

0.83

 houſe

0.81

 ſeveral

0.81

 AssemblyCulture

0.81

 againſt

0.78

 Reſ

0.78

ſelf

0.77

Activations Density 0.199%

No Known Activations