INDEX

Explanations

<!DOCTYPE html, Q, GT, Inspiration

The neuron activates on numeric literal tokens (integers or floats) in code snippets.

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

ńst

-1.48

 meiner

-1.41

]$}

-1.40

↵↵↵

-1.36

 możemy

-1.34

 населения

-1.34

僕は

-1.33

นี้

-1.32

 unserer

-1.31

jei

-1.30

POSITIVE LOGITS

</i>

1.65

跺

1.42

特别是

1.40

</strong>

1.38

 maestros

1.38

ätigung

1.34

致します

1.34

gages

1.34

倏

1.33

Ḳ

1.31

Activations Density 0.003%