INDEX

Explanations

code structure followed by values

The neuron activates on numeric literals (multi-digit numbers) in the 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

its

-1.38

Интере

-1.30

Моя

-1.24

Сколько

-1.24

它的

-1.23

eraard

-1.22

Эти

-1.22

 대해

-1.20

いよいよ

-1.20

 weißem

-1.20

POSITIVE LOGITS

you

1.62

 there

1.59

!!!

1.41

1.40

 only

1.37

1.35

in

1.35

The

1.34

<>

1.34

1.33

Activations Density 0.004%