INDEX

Explanations

code, commands, configuration

The neuron fires on programming‐style identifiers (library or API names, function calls, class/module names, etc.).

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

此外

-1.45

-1.37

 huset

-1.37

 netts

-1.34

şil

-1.30

俣

-1.27

 رون

-1.27

Confira

-1.27

 estekak

-1.27

 parfois

-1.27

POSITIVE LOGITS



1.59

 that

1.54

 червня

1.48

 eficaz

1.47

if

1.45

or

1.39

 when

1.38

 quickly

1.34

 dispozici

1.34

 such

1.33

Activations Density 0.044%