INDEX

Explanations

format specifiers like %e, %p

The neuron is strongly triggered by numeric tokens (digits and decimal‐point number fragments) 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

 internas

-1.33

💃

-1.29

tobe

-1.25

gradable

-1.25

."/

-1.24

🙊

-1.24

℉

-1.24

/");

-1.23

}>

-1.23

᯾

-1.22

POSITIVE LOGITS

now

1.49

––

1.36

ܣ

1.28

 рассказывает

1.25

 теперь

1.25

 inzwischen

1.20

 Enlarged

1.20

 Vomiting

1.19

 Parenthood

1.17

 mammoth

1.16

Activations Density 0.001%