INDEX

Explanations

starting sentences with i

This neuron selectively activates on the first-person singular pronoun “I.”

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

-1.87

 και

-1.80

 that

-1.79

 medarbe

-1.79

or

-1.78

.,

-1.77

 surgir

-1.75

欷

-1.70

 начин

-1.70

 increíbles

-1.69

POSITIVE LOGITS

 “(

2.13

’)

1.73

注意事

1.67

на

1.67

“

1.62

῞

1.55

 höhere

1.55

 notare

1.54

1.53

 impon

1.52

Activations Density 0.001%