INDEX

Explanations

programming language constructs

The neuron activates on numeric literals (integer or floating-point numbers) in code.

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

<td>

-1.59

Having

-1.37

){

-1.30

);

-1.28

}_{

-1.24

-1.23

 всех

-1.23

That

-1.21

擁有

-1.20

},

-1.19

POSITIVE LOGITS

۳

1.48

۴

1.47

absolutely

1.46

٢

1.44

 ajouter

1.39

۲

1.36

 poign

1.35

۵

1.34

amazing

1.33

۸

1.31

Activations Density 0.035%