INDEX

Explanations

Star Wars and Star Trek

The neuron detects mentions of the film franchise “Star Wars.”

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

\&

-2.20

スポンサーリンク

-1.98

\&

-1.94

ton

-1.85

衞

-1.84

 anche

-1.83

 también

-1.80

 yarar

-1.75

//

-1.75

</h2>

-1.75

POSITIVE LOGITS

퐶

2.09

嫋

1.69

再

1.66

便

1.63

低声

1.61

鸝

1.61

 Guia

1.59

 Controle

1.59

 absolument

1.58

嗵

1.57

Activations Density 0.003%