INDEX

Explanations

things in lists

The neuron detects category or heading words—single-word labels used to enumerate or classify items (e.g. business/personal, phone/mail, movies/books/TV, age/sex).

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

and

-8.75

и

-2.58

และ

-2.33

 και

-2.17

 oraz

-2.06

và

-1.92

 এবং

-1.91

및

-1.91

 และ

-1.87

和

-1.87

POSITIVE LOGITS

 cioc

1.73

1.70

toxicity

1.70

çou

1.65

まりました

1.60

 fréqu

1.60

 tinte

1.60

まります

1.59

 sabias

1.57

 manquer

1.55

Activations Density 0.089%