word right before a number or year

What this neuron does

This neuron fires on the word just before a number, such as the word 'the' in 'At the' before a census year, or 'are' before an age. It goes quiet or negative on dates and numbers themselves. Turning it up made the text wander without a clear theme.

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

   Jeddah in Saudi Arabia, which will build the foundation for the King Abdulaziz Marine Museum.<|endoftext|>By clicking on CONTINUE you confirm that you are 18 years and over.⏎Note: to turn off these warnings you need to

2. #2 peak

   light(s). It turns out, perhaps somewhat surprisingly, that there is a simple and intuitive 2-D image-based geometric analysis that can verify the authenticity of shadows.⏎Locate

3. #3 peak

   not approved by the U.S. Food and Drug Administration (FDA) as a treatment for cancer or any other medical condition. The term laetrile comes from 2 words (laevorotatory and mandelonitrile) and is

4. #4 peak

   is located on U.S. Route 101 on the shores of Humboldt Bay, north of San Francisco and south of the Oregon border. At the 2010 census, the population of the city was 27,

5. #5 peak

   , depending on the specifications, you want to return the value from either column B, C or D and so on. In such case, we are speaking of 2D lookups or a two way lookup. So we search in both rows

6. #6 peak

   at Lachine and cuts through the southwestern part of the island, it 1970 it was closed to shipping. Lachine was replaced by the

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

   a name submitted by India.⏎Where do these names come from? Find out here.<|endoftext|>Testing the Waters for Contaminants⏎Mon, 11/01/2010 - 12:1

2. #2 peak

   Jake Matijevic."⏎- Curiosity on Mars sits on rocks similar to those found in marshes in MexicoTue, 30 Oct 2012, 11:07:

3. #3 peak

   of pollen grains diverging. Air sac<|endoftext|>Wednesday, March 11, 2009⏎rothbard on the utility of

4. #4 peak

   for Lord Krishna. Dwapara Yug<|endoftext|>Simple technique appears to be safe and effective, review suggests⏎By Robert Preidt⏎MONDAY, Oct. 15 (HealthDay News) -- A technique called the "mother's kiss

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.