INDEX

Explanations

existence of .

The neuron specifically fires on occurrences of the word “existence.”

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

橚

-1.88

釤

-1.73

 vixion

-1.72

非常好

-1.70

 restera

-1.67

opic

-1.65

哧

-1.63

");

-1.60

 westfalen

-1.57

ль

-1.56

POSITIVE LOGITS

2.31

an

1.91

}$,

1.54

ଃ

1.52

 Offers

1.52

Выводы

1.48

’

1.44

on

1.41

大力

1.38

and

1.38

Activations Density 0.019%