INDEX

Explanations

European things

The neuron flags geographic or ethnic demonyms—especially “European” and related continental adjectives.

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

 they

-2.23

is

-2.22

initializeApp

-1.91

 were

-1.75

-1.59

();

-1.56

]]);

-1.55

()]);

-1.55

 berbagai

-1.55

it

-1.55

POSITIVE LOGITS

🌇

1.71

 pained

1.57

ją

1.55

лтемелер

1.54

Væ

1.50

 diesen

1.48

veien

1.48

 einzel

1.48

lloworld

1.45

Activations Density 0.020%