INDEX

Explanations

professional presence

This neuron detects numeric tokens containing decimal points (i.e. floating-point numbers).

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

</em>

-1.73

 únicamente

-1.70

 présence

-1.68

 otorg

-1.65

 هذه

-1.59

⦊

-1.56

ELINES

-1.56

 increase

-1.55

of

-1.54

 fazia

-1.54

POSITIVE LOGITS

</h1>

2.75

ali

1.96

1.94

re

1.91

1.87

1.83

 资料

1.79

1.77

our

1.73

an

1.72

Activations Density 0.023%