INDEX

Explanations

LaTeX commands and Python regex

The neuron mainly activates on numerical tokens—especially numbers (including multi‐digit and decimal values).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

^*$

0.55

){

0.54

 proven

0.54

 calculations

0.52

 ground

0.52

 tropics

0.52

 country

0.52

 signature

0.52

 fast

0.51

 measurements

0.51

POSITIVE LOGITS

 전혀

0.61

bursement

0.61

ídio

0.61

JUST

0.60

Ꮇ

0.60

 অনুষ্ঠান

0.59

otherapeutic

0.59

 Paryayvachi

0.59

añas

0.59

úst

0.58

Activations Density 0.000%