INDEX

Explanations

class/method names

The neuron activates on numeric literals (digits) 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

-1.52

-1.34

-1.33

</i>

-1.31

</u>

-1.31

</strong>

-1.30

-1.28

-1.27

-1.26

-1.24

POSITIVE LOGITS

↵

2.16

↵↵

1.95

これは

1.34

’).

1.31

:✨

1.29

kozások

1.29

<0xA3>

1.25

 quiser

1.22

if

1.20

 capabilities

1.20

Activations Density 0.066%