INDEX

Explanations

negative numbers

The neuron activates on numeric literals (integers and floating‐point 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

pozycji

-1.43

-1.40

ките

-1.34

 perdiendo

-1.30

くらいで

-1.30

 arrancar

-1.29

["

-1.28

我们的

-1.27

 luces

-1.26

лочка

-1.25

POSITIVE LOGITS

for

2.16

of

1.53

 ameste

1.46

 användas

1.41

 because

1.40

 since

1.39

as

1.36

 legislación

1.34

 anything

1.34

in

1.34

Activations Density 0.031%