INDEX

Explanations

the word "image" and similar terms in code/markup contexts

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

ConverterFactory

-0.62

 filming

-0.59

 cartoons

-0.59

📽

-0.57

AutoField

-0.56

Lud

-0.54

 سينما

-0.52

lud

-0.51

DVD

-0.51

 vide

-0.50

POSITIVE LOGITS

 Image

2.11

 IMAGE

2.02

 image

2.00

Image

1.94

image

1.88

IMAGE

1.86

 Images

1.73

 images

1.71

images

1.70

Images

1.66

Activations Density 0.312%