unclear: 'of' after a noun

What this neuron does

This neuron mostly reacts to the word "of" that follows a noun, like "side effect of" or "source of", but it also goes strongly negative on "of" in similar spots, so the pattern is hard to pin down. Turning it up did not produce a clear theme.

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

   ophagus; (2) clavicular, frequently merging into a single interclavicular sac; (3) anterior thoracic, on the abdominal wall of the thorax; and (4) posterior thoracic, on the dorsal side

2. #2 peak

   lenses to direct and concentrate sunlight onto a solar cell of smaller area. Most concentrator arrays must directly face or track the sun. They can increase the power flux of sunlight hundreds of times.⏎Conductor — The material through which electricity is transmitted,

3. #3 peak

   . Dizziness is also a common side effect of certain prescription drugs.⏎Dizziness in people with bleeding disorders can be especially dangerous,

4. #4 peak

   . The discrete model of exponential growth is ; where the first term is , and is the common ratio. The continuous model is .⏎1. Find the common ratio of each geometric sequence.⏎

5. #5 peak

   on its histology by investigators. Extraovarian primary peritoneal carcinoma (EOPPC), serous surface papillary carcinoma, papillary serous carcinoma of the peritoneum, extra ovarian Mullerian adenocarcinoma,

6. #6 peak

   , strawberry and chocolate Neapolitan ice cream of your childhood. The actual flavors of the neutrinos come from their association with other

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

   ⏎Intentional fitness - Use of functional equipment⏎Teacher role modeling of all lessons⏎Core curriculum content integration⏎Physical

2. #2 peak

   Turbojet and turbofan are jet engines. Some aircraft, notably gliders, do not have an engine. To take off they must have another source of thrust - that is, the tow-plane which pulls them into the air.⏎Within

3. #3 peak

   1N4007 PN junction diodes and a filter capacitor of 2.2uF/450V.⏎This<|endoftext|>Warning: Use of undefined constant user_level - assumed 'user_level' (this will throw an Error

4. #4 peak

   check for cavities, and plenty of education for the family on cavity prevention.⏎This includes information about diet and nutrition, use of fluoridated toothpaste, and preventing bacteria that cause cavities passing from parent

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.