INDEX

Explanations

information, descriptive labels, sections

The neuron fires on isolated headings or section‐title labels (e.g. standalone words like “Information,” “Overview,” “Profile,” “Feature,” etc.).

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

؛

-1.40

</u>

-1.30

 cruda

-1.27

、

-1.20

 cristiana

-1.20

 connue

-1.18

 velha

-1.16

 maestra

-1.16

 метров

-1.15

 груди

-1.15

POSITIVE LOGITS

and

2.48

 jego

1.48

 instead

1.33

 based

1.30

livejournal

1.30

 цього

1.23

 while

1.20

ไลน์

1.19

 actually

1.18

 ネタバレ

1.18

Activations Density 0.186%