INDEX

Explanations

media, sports, and academic categories

The neuron activates on nouns naming tangible or cultural “items” or works—e.g. cars, auctions, articles (“piece”), tracks, albums, songs, films, documentaries, books, and series.

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

it

-2.31

}^{*}\

-1.51

 things

-1.40

 comunión

-1.38

 there

-1.38

 terlalu

-1.35

læg

-1.33

mıştır

-1.27

.${

-1.27

 mascarilla

-1.27

POSITIVE LOGITS

to

2.13

of

1.52

on

1.36

fillment

1.24

all

1.20

 ebenfalls

1.18

 före

1.14

 formerly

1.14

lo

1.13

by

1.13

Activations Density 0.221%