INDEX

Explanations

of [number]

The neuron never activates on any of the shown text—it does not reliably detect any pattern.

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

 which

-1.94

is

-1.75

 whose

-1.68

teady

-1.65

们的

-1.61

 last

-1.59

 considère

-1.56

᎒

-1.53

 ones

-1.53

隐隐

-1.52

POSITIVE LOGITS

 étrange

1.86

1.85

 impré

1.77

点此

1.75

1.71

潆

1.63

ஂ

1.62

</sup>

1.62

Достоинства

1.60

of

1.59

Activations Density 0.002%