"can" after a noun in a clause

What this neuron does

This neuron fires on the word "can" when it follows a noun or pronoun inside a clause, as in "things you can do" or "those that can grow". Turning it up did not produce a clear change in the writing, so the effect is hard to see.

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

   Abandoned Places in the World article.⏎Are you interested in visiting places that have been abandoned? Or is it too creepy? Have you been to any that you can add to the list? Please share below!<|endoftext|>How to tell if lines

2. #2 peak

   on has a rating of 4, and Malawai has a rating of 1.3.⏎Working individually, take five minutes to briefly write down what you can surmise from the map, addressing these questions:⏎- What patterns do you see

3. #3 peak

   antibiotic. The antibiotic knocks out cells which do not have the resistant marker. Those bacterial colonies that can grow have successfully taken up and expressed the introduced genetic material.⏎An alternative to a

4. #4 peak

   is even off the table for those with insufficient literacy skills. 75% of 17-24 year olds in this country can’t meet minimum requirements for military service3.⏎Inability to find employment has long

5. #5 peak

   our kids sense of identity, and very importantly, increases their ability to stand up to peer pressure. According to his studies, those children and teenagers that can effectively argue with parents are 40% more likely to say “no”

6. #6 peak

   suffered a traumatic brain injury, and is now cared for by her family, 24 hours a day 7 days a week. Hannah wears a diaper, can’t feed herself, talk, or walk. The driver responsible sentenced Hannah to life

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

   sum of money to support them and they both are euqally friendless in the town of Brussels. Will chance once again intervene? Will life<|endoftext|>You can help keep your heart and blood vessels healthy by taking steps toward a healthier lifestyle. These

2. #2 peak

   …[Read more]<|endoftext|>To actually reduce pounds in a healthier manner, it is perfect to burn fat gradually. And incredibly, most professionals consent which you can accomplish by using a diet regime. As opposed to a extreme life-style change, the

3. #3 peak

   is perfect, implying that the signatures have been guillotine – trimmed on all four edges, it cannot be rebounded in the traditional way. This is because a perfect binding eliminates the folded edge of

4. #4 peak

   out your supplies, and follow the rebinding process in this chapter.⏎Inspect your book; whether it is a hardback or paperback, it can easily be rebounded if its signatures are folded and sewn. However, if the binding

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.