INDEX

Explanations

identifiers and subsequent entities

This neuron responds to metadata byline markers—specifically the token “author.”

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 their

-1.75

and

-1.46

or

-1.41

 from

-1.40

natured

-1.36

unjung

-1.34

 changed

-1.33

韪

-1.30

 observa

-1.28

 began

-1.25

POSITIVE LOGITS

 stalwart

1.47

 ailing

1.46

specifically

1.39

我真的

1.38

within

1.38

 herido

1.38

 REALLY

1.37

 horrifying

1.36

 scorching

1.36

Activations Density 0.000%