INDEX

Explanations

listing items within a group

The neuron activates on numeric tokens—plain numbers or numeric values (including decimals) 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

addGroup

-1.27

>);

-1.26

тился

-1.22

поді

-1.20

늄

-1.17

addWidget

-1.16

简称

-1.16

}`}>

-1.15

)++;

-1.15

hogany

-1.15

POSITIVE LOGITS

烀

1.48

niños

1.41

 però

1.41

 แต่

1.36

 Nhưng

1.34

 trouvé

1.33

 nového

1.30

欷

1.29

 lustig

1.28

 niekoľ

1.28

Activations Density 0.026%