INDEX

Explanations

references to skulls or skull-related imagery

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

AttributeSet

-0.57

dientemente

-0.57

hlin

-0.57

ьаж

-0.56

AnchorTagHelper

-0.54

 وابسته

-0.52

beforeSend

-0.52

lovakia

-0.49

glEnd

-0.49

TagHelper

-0.49

POSITIVE LOGITS

 skull

3.52

 Skull

2.75

 skulls

2.70

skull

2.41

Skull

2.30

 cráneo

1.38

 calavera

1.02

 cranial

0.84

 чере

0.82

 skul

0.74

Activations Density 0.001%