INDEX

Explanations

the expression of enjoyment or fun

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

func

-1.05

 Funny

-0.93

 laughing

-0.92

Funny

-0.90

 laugh

-0.90

FUN

-0.87

 laughed

-0.86

 enjoying

-0.86

 enjoy

-0.85

 Enjoy

-0.85

POSITIVE LOGITS

fun

1.30

دانشنامهٔ

0.79

 lenker

0.71

 متحده

0.68

 behulp

0.68

 surla

0.66

 ویکی‌پدیای

0.65

 écoulé

0.63

AddTagHelper

0.62

 ويكيميديا

0.60

Activations Density 0.004%