'of' after a noun in titles

What this neuron does

This neuron fires on the word 'of' when it follows a noun in a title or description, such as 'Anatomy of' or 'study of'. The effect is weak, and turning it up did not produce a clear change in the model's writing.

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

   that changes how the⏎cd command works. Normally when you try and cd⏎into a directory, it will only try and change to the path specified from the current directory

2. #2 peak

   or less). Thus began the era of dancing babies and other horrors best forgotten<|endoftext|>PROTEOMICS is the study of many proteins at once- or a description of proteins in a cell, tissue or cellular organelle on a global scale.⏎

3. #3 peak

   , the dry ice temperature of -78 C is well below its flash point at <|endoftext|>Henry Gray (18251861). Anatomy of the Human

4. #4 peak

   father brings with him.⏎After sharing the story your child might like to plant some beans like Azzi does and watch them grow or make spicy beans⏎The Colour of Home⏎Mary Hoffman, illus. Karin Littlewood⏎Hassan

5. #5 peak

   a child knows letters of the alphabet and their sounds. Children learn letters when they look at their names and other children’s names during Welcome.⏎- Meaning and use of print is when a child knows that writing has meaning. Corps members and children write

6. #6 peak

   stated Sarah Korona, EVA flight controller at NASA’s Johnson Area Middle in Houston. “EVA” stands for extravehicular exercise.⏎The anatomy of a spacesuit⏎A spacesuit is made up of practically a half dozen completely

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

   analysis, we rely on the inflation “heat map” shown below, which uses color coding similar to that of weather maps to distinguish the items with the most significant increases or decreases in inflation from

2. #2 peak

   625 a year (based on 12,000 miles of driving per year and $3.79 a gallon, nationwide average as of 5/19/2

3. #3 peak

   , it is generally best not to amend the soil used to fill a planting hole. Fill around the root ball of the tree or shrub with the same soil that was dug out of the planting hole.⏎It also is not recommended to dig the

4. #4 peak

   do something about drift, we invented the an air monitoring system we call the "Drift Catcher." It's affordable, robust and based on the same technology used by the California Air Resources Board in its studies.⏎The big idea? Put

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.