INDEX

Explanations

"About" following phrase

This neuron detects numeric tokens representing measurements or quantities—especially decimal numbers indicating things like duration, location codes, prices, or capacities.

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

0.94

：

0.77

0.71

:\

0.70

':

0.66

():

0.64

0.63

**:

0.62

:'',

0.61

!:

0.61

POSITIVE LOGITS

 répart

0.67

 वायरल

0.57

 sóng

0.57

 пропа

0.56

 colère

0.55

ὄ

0.55

 polvo

0.54

 всеки

0.54

 plötzlich

0.54

 transferência

0.54

Activations Density 0.001%