INDEX

Explanations

mentions of bleeding

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

ciaux

-0.65

AndEndTag

-0.62

ük

-0.55

bruck

-0.53

="{

-0.52

 Most

-0.51

 Кан

-0.50

noční

-0.50

 Last

-0.49

.…

-0.49

POSITIVE LOGITS

 Bleeding

1.23

 bleeding

1.11

hagic

1.08

Bleeding

1.05

 bleed

1.04

 bleeds

1.04

orrhage

1.03

 hemorrhage

1.02

 hemorr

0.95

 bled

0.91

Activations Density 0.005%