INDEX

Explanations

codes and data syntax

The neuron activates on numeric tokens (literal numbers) in the text.

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

all

-1.90

 Despite

-1.88

 Although

-1.85

With

-1.83

in

-1.81

 unrelenting

-1.81

 .....

-1.80

 With

-1.80

!!!!!

-1.79

Despite

-1.77

POSITIVE LOGITS



1.93

 legendar

1.82

 erhi

1.77

 zoude

1.76

怱

1.75

יבור

1.71

ほとん

1.70

 cérami

1.63

 dando

1.63

 Dinas

1.63

Activations Density 0.105%