INDEX

Explanations

):

The neuron fires on numeric literals (sequences of digits) 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

其妙

-2.78

 escalier

-2.31

咴

-2.20

居る

-2.11

𓆉

-2.08

 помощи

-2.05

ors

-1.98

 cuillère

-1.98

 début

-1.98

 ausein

-1.97

POSITIVE LOGITS

</h2>

2.23

 reconoci

2.14

):

2.09

 asegur

2.06

){

2.06

 conoci

2.05

 otros

1.99

越大

1.96

 muerta

1.96

 quedará

1.95

Activations Density 0.012%