INDEX

Explanations

family and relations

The main thing this neuron does is detect mentions of family or kinship (e.g., “family,” “relations,” “generations,” “matriarch”).

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

</b>

-1.48

-1.38

</code>

-1.36

].

-1.36

</i>

-1.34

</h1>

-1.24

↵↵↵↵

-1.23

</th>

-1.22

↵↵↵

-1.22

/**

-1.20

POSITIVE LOGITS

 afterward

1.38

family

1.23

 afterwards

1.22

 familiale

1.20

 thus

1.20

できるので

1.20

 trattano

1.18

 after

1.17

 thereafter

1.17

 carbón

1.16

Activations Density 0.029%