the modal 'can' after 'there' or 'it'

What this neuron does

This neuron lights up on the word "can" when it means "is possible", especially in phrases like "there can be" or "it can be". When it was turned up, the model got stuck repeating "can't be able to", so this neuron seems tied to talking about what is possible.

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

   be done when the beetle is dormant to prevent further spreading, Eddy says. She adds, "There is no one textbook way of dealing with this because there can be so many different circumstances."⏎For now, the city wants to educate residents about

2. #2 peak

   had access to more general care, the physical body second. This has all changed in the past few years.⏎Mental health professionals and organizations now know that there can't be a separation between a brain and body when it comes to effective psychiatric treatment

3. #3 peak

   ose rich foods. For these people there can be many negative side effects to ingesting dairy products that include but are not limited

4. #4 peak

   the various agencies are getting closer and closer to finding aliens, while at the same time, we have almost no idea about how powerful the military technologies of the aliens can be and whether they will be friendly to the human or not; I start to

5. #5 peak

   Icon (1954). They correctly criticized the belief that the intention of the author was the one and only correct interpretation of a work. Certainly, there can be other valid interpretations of a work, and of course the literature scholar should not

6. #6 peak

   know how difficult it can be to get into a story and then keep readers engaged while they wait for 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

   -ethnic neighbourhoods in England, by Dr Gemma Catney, Professor Richard Wright, and Professor Mark Ellis. The original article, posted in Geography Directions, can be accessed here. You can also read the full article published in Transactions of the

2. #2 peak

   that he would eliminate most U. S. cabinet departments, including those overseeing commerce, education, energy, and labor (some of this material and references for it can be found in my An Age

3. #3 peak

   You can see where it is in the solar system on the JPL Small Body Database Browser. Here is the map for today:⏎As you can see in the map, it's a main belt asteroid, orbiting the Sun

4. #4 peak

   a sentence that is split over several lines in HTML. </BODY> </HTML>When this is displayed by Mosaic, it will look like:⏎As you can probably guess, commands are enclosed in angle-brackets <>, so that the HTML

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.