INDEX

Explanations

programming, ui, and specific nouns

The neuron responds to unusually long individual tokens (i.e. long words).

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

↵↵

-2.95

-2.61

–

-2.56

-2.48

-2.34

</i>

-2.33

 make

-2.28

-2.25

あります

-2.19

POSITIVE LOGITS

 serían

2.83

淠

2.73

 permanece

2.59

...";

2.58

...',

2.52



2.50

yarakat

2.48

 سامسون

2.45

 actúa

2.45

 ſaid

2.41

Activations Density 0.008%