INDEX

Explanations

citations and links

The neuron activates on numeric citation and reference markers (e.g. bibliography entries, footnote brackets, and standalone numbers).

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

and

-1.30

nosť

-1.20

();

-1.16

ColumnHeaders

-1.13

 atraer

-1.13

免費

-1.10

 empuj

-1.09

ไม่มี

-1.02

 natures

-1.01

>";

-0.99

POSITIVE LOGITS

 including

1.42

including

1.29

http

1.27

 difficiles

1.26

 this

1.25

see

1.23

See

1.22

 actually

1.21

Including

1.20

 mouseY

1.20

Activations Density 0.008%