INDEX

Explanations

above and below

The neuron fires on call-to-action navigation instructions (e.g. “click the button below,” “see links below,” 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

 générer

-1.33

 使っ

-1.32

 داشتم

-1.27

still

-1.25

āciju

-1.24

 băr

-1.18

越来越

-1.17

ovací

-1.16

 they

-1.15

 acolo

-1.15

POSITIVE LOGITS

for

1.52

to

1.41

of

1.33

’

1.27

at

1.22

 Кубка

1.22

1.20

washingtonpost

1.19

 nicht

1.17

 available

1.16

Activations Density 0.029%