INDEX

Explanations

binary digits 0 and 1

The neuron consistently activates on standalone numeric tokens (digits and numbers) in the text.

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

of

-1.51

the

-1.37

shiro

-1.36

-1.32

-1.31

on

-1.24

-1.23

ad

-1.21

and

-1.20

POSITIVE LOGITS

cuencia

1.34

 dạ

1.34

struzioni

1.33

icoot

1.30

 extremadamente

1.27

atív

1.27

пасибо

1.23

 ORGANISM

1.21

ços

1.20

 <=",

1.19

Activations Density 0.061%