INDEX

Explanations

The neuron strongly activates on words naming or labeling media types or creative‐work headings—e.g. “show,” “track(s),” “Original Song,” “MV,” “short story,” “film,” “franchise,” “album,” “NEW RELEASE,” etc.

media releases and titles

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

-1.22

as

-1.19

-1.18

 there

-1.17

 could

-1.10

-1.09

all

-1.07

了两

-1.05

POSITIVE LOGITS

 brune

1.47

และ

1.45

 salles

1.34

――

1.33

 pneus

1.27

 principes

1.26

 netto

1.23

 pittores

1.23

 intelligente

1.23

ología

1.22

Activations Density 0.129%