INDEX

Explanations

suburban areas

The neuron activates on mentions of “suburb” and its variants (e.g., suburb, suburbia, suburbs, suburban).

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

饪

-2.19

 This

-2.17

It

-2.14

 démocratique

-2.11

];

-2.09

梘

-2.03

嵜

-1.95

 batal

-1.93

']")

-1.88

ve

-1.88

POSITIVE LOGITS

↵↵

2.52

2.44

 suburbs

2.25

’

2.20

中医

2.19

2.14

 suburb

2.09

2.06

 ideally

2.03

Activations Density 0.006%