INDEX

Explanations

keyframes, Krugman, Kilkenny, New Deal, Tocqueville, Swinney

The neuron predominantly activates on numeric tokens (including integers and decimal numbers).

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

’.

-2.52

’,

-2.48

’

-2.31

↵

-2.27

,’

-2.22

?’

-2.09

,’”

-2.09

”,

-2.08

 “.

-1.98

!’

-1.96

POSITIVE LOGITS

ยัง

2.27

𓍊

1.84

 Keynes

1.76

 fotografii

1.75

 pomoci

1.73

naies

1.72

 baterie

1.70

 nowego

1.67

wirk

1.66

лата

1.63

Activations Density 0.001%