"of" after amounts of land

What this neuron does

This neuron lights up on the word "of" when it comes right after an amount of land, like "acres of" or "tract of", and the next word is likely to be "land". When it was turned up, the model kept saying "land" over and over.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

   1878, as the Missouri, Kansas and Texas Railroad was making its way into the state, New York investor William Whitewright purchased a tract of land in the railroad’s right-of-way. He surveyed a town site and then

2. #2 peak

   ⏎In Early 2015, the founder and director of Borderlands Restoration were presented with a unique opportunity; over 1,000 acres of nearly pristine grassland,

3. #3 peak

   the mouth of the Little Miami. Early entrepreneurs Israel Ludlow, Matthias Denman, and Robert Patterson purchased from John Cleves Symmes 800 acres of land and created the second settlement opposite the mouth of the Licking River. The

4. #4 peak

   counter to the predominant belief that high-yield farming is bad for the planet.⏎Typically, the practice of squeezing out as much food as possible from a parcel of land is associated with over-application of fertilizers and pesticides, extensive soil erosion,

5. #5 peak

   all wildlife encountered on the trail<|endoftext|>In 1847, when Mormon pioneers arrived in the Salt Lake Valley, LDS Church president Brigham Young selected a plot of the desert ground and

6. #6 peak

   forest protection by buying tracts of land, but which often fail to address the needs or rights of local Indigenous peoples

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

   image above, the TA is a thick layer of muscle. The transverse abdominal muscle wraps around the torso from front to back and the muscle fibers of the TA run horizontally, similar to a corset

2. #2 peak

   Exercises To Help You Avoid Injury⏎Well + Good reports on iliotibial band syndrome (ITBS), the most common overuse injury of the tendon that runs from the outside part of the hip across the hip and the knee joints.⏎Well

3. #3 peak

   ?⏎The spine runs down the middle of the back. A healthy spinal cord is completely straight with all

4. #4 peak

   4. Today, state-of-the-art, innovative technologies are still based on discoveries made by researchers nearly<|endoftext|>The material in fridge magnets is magnetised in strips that run the length of the material, forming a Halbach Array. The result of this

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.