towns and population nouns

What this neuron does

This neuron fires on words for a place or its people, like 'town', 'world' and 'population', mostly in descriptions of towns and census-style facts. When it was turned up, the replies were unrelated, so the steering does not confirm the pattern.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   were 106 housing units at an average density of 1.1 per square mile (0.4/km²). The racial makeup of the town

2. #2 peak

   : Caligine II is a small moon orbiting the Gas Giant Caligine. Before the Great Crusade, Caligine II was a bustling mining world that at its peak employed more than 3,000,00

3. #3 peak

   inevitably ruined by uncontrolled use.⏎The metaphor that Hardin uses to explain the concept is that of a community common or park on which the town’s people bring their cows to be fed. In the back of everyone’s mind

4. #4 peak

   there three years before Fowler’s 1891 arrival, and there might have been as many as 1,500 persons living in Whitewright by 1890.⏎Fowler pictured the city from the southeast just

5. #5 peak

   the planet…⏎Power Our Cities With Tornadoes⏎A tornado generates enough energy to power a small town. They’re widespread and frequent these days, but no one can harness all that

6. #6 peak

   in publicly accessible overlays powered by ArcGIS. In addition to flood mapping, overall mitigation strategies are tracked using the same technology, with 87 percent of the population currently residing in areas with approved mitigation plans (FEMA, 202

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

1. #1 peak

   intervention model in Chinese: A growth model of reading fluency. Paper presented at the Twenty-First Annual Meeting: Society for the Scientific Study of Reading, Santa Fe, New Maxico.⏎- Response to intervention<|endoftext|>Much of the current interest in

2. #2 peak

   1832, he studied law and was admitted to the bar, practicing first at Boston and later at New York. He served for some years in the Massachusetts legislature, but at length devoted himself to the writing of legal text-books and the

3. #3 peak

   receive a confirmation email containing information about joining the webinar.⏎Research, Development & Demonstration Department Webinar Workshop for the 2021 Research Plan⏎SoCalGas® Research, Development & Demonstration (RD&D) staff conducted a stake

4. #4 peak

   exterity, enabling them to do many of the same things as rigid neuroprosthetics.⏎Amputees with a team of engineers from MIT and Shanghai Jiao Tong University tested the prosthetic hand through a range of everyday activities – zipping a

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.