INDEX

Explanations

verification and origin

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 downstream

-0.81

 upstream

-0.79

 authentic

-0.77

authentic

-0.74

upstream

-0.71

 authentique

-0.65

 authenticity

-0.65

djangoproject

-0.63

Authentic

-0.61

AddTagHelper

-0.61

POSITIVE LOGITS

er

0.74

ally

0.73

ness

0.71

ening

0.71

ly

0.69

ers

0.68

ating

0.68

ity

0.65

0.64

ting

0.63

Activations Density 0.069%