"what" after verbs of knowing

What this neuron does

This neuron fires on "what" after words like "know", "find out", or "shows", as in "find out what the Gospels are". It is most negative on "a" or "an" right before the word "example" or "list". Turning it down made the text loop on the word "example".

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

   30 grams of protein at each meal to optimize muscle protein synthesis. Though most people eat a combination of protein-containing foods at each meal, this infographic shows what 25 grams of protein from different sources looks like.⏎Researchers in Ireland recognized

2. #2 peak

   assistance was required several times a day. For a description of what is included in each of these activities, please see the Glossary.<|endoftext|>Mad

3. #3 peak

   is for adults 19 years of age or older. It does not apply to pregnant or breastfeeding women, because they have different nutritional requirements. Once you know what you need the most, the next logical step is to add supplements of those vitamins

4. #4 peak

   Write About, I’m obviously partial to a publishing platform that incorporates visual writing ideas and customized user groups.⏎3. Communicate with parents.⏎Explain to parents what a blog is and why it can be a powerful tool. Ask for their feedback

5. #5 peak

   patristic texts?⏎1. Did Mary merit to be the Mother of God?⏎2. Find out what the apocryphal Gospels are and of what value they are.⏎

6. #6 peak

   and on-line practice.⏎GED Math - What to Expect⏎Are you considering earning your GED? Take away some of the fear of math by knowing what to expect.⏎How to Find Common Factors⏎An Efficient Method to Find Common Factors

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

   or not and take the default route. Here’s an example of⏎mwhen for Monoids:⏎-- Important numbers!⏎xs = [

2. #2 peak

   , but all recalls are listed in FDA’s weekly Enforcement Reports. See a list of vaccines that have been recalled in the past few years. ⏎Parents ought

3. #3 peak

   test numbers. If you⏎determine that num is not divisible by 5 and 7, then increase⏎count by one.⏎Share your code⏎Show a friend, family member, or teacher what you've done!<|endoftext|>cigarette

4. #4 peak

   citizens, including a more democratic government with greater powers given to civilians and less power given to military officials. There are many articles contained within this document, and here are some of the main ones:⏎1) Section 1 – The people shall be

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.