'mountain' before the word 'range'

What this neuron does

This neuron lights up on the word 'mountain' when it comes right before 'range', as in 'Andes mountain range'. Its opposite side reacts to 'ranging' and 'range' used to mean a spread of values. Turning it up made the model write about 'interval' again and again, which is loosely related to ranges.

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

   841 ft), Cerro Aconcagua holds the title as the highest mountain in the Americas and the highest mountain outside Asia. Located in the Andes mountain range of Argentina, Aconc

2. #2 peak

   5,621 m (18,442 ft) in its eastern summit. It is an inactive volcano found in the western Caucasus mountain range in Kabardino-Balkaria and Karachay-Cherkessia

3. #3 peak

   western foothills."⏎Temple Crag displays some of the famous Sierra Nevada granite. The highest peaks in the Sierras are located along the eastern edge of the mountain range. Geologists suspect that inflowing mantle material in the east is repsons

4. #4 peak

   as dark rocks on the white ice. Most meteorites are found in icefields close to the Transantarctic Mountain range – you can see a map where all the yellow labels mark places that meteor

5. #5 peak

   the archipelago’s land surface. The fold in the Earth’s crust that formed the Kornati mountain range was produced by the collision of the Adriatic and European tectonic plates

6. #6 peak

   itudes. They cover broad east-west bands near 30 degrees north and south latitude.⏎Middle latitude semiarid and desert climates are in the rain shadows of mountain ranges. Winds that descend the<|endoftext|>Genital/ perigenital infection caused by

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

   float freely in space, beyond our galaxy's grasp.⏎The new Local Group members are even smaller and fainter than other known dwarf galaxies, with luminosities ranging from only a thousand to at most a few hundred thousand times that of our Sun

2. #2 peak

   52 can be seen from Earth with binoculars.⏎Due to interstellar absorption of light, the distance to M 52 is uncertain, with estimates ranging between 3,000 and 7,000 light years

3. #3 peak

   in the Piedmont. Near the type location, mean annual air temperature is 59 degrees F and mean annual precipitation is 45 inches. Slopes range from 4 to 60 percent.<|endoftext|>RIVERSIDE, Calif.

4. #4 peak

   the scene of becoming the most prominent region producing agricultural production Southeast Asia has a rich environmental and agricultural diversity. Almost all of the region is mountainous, and temperatures range from lowland areas to mild climates in the highlands.⏎In addition, there

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.