'to' after 'what' or 'where' (what to do)

What this neuron does

This neuron fires on the word 'to' when it follows 'know what' or 'where', as in 'know what to do' or 'where to start'. It is pointing at the start of a phrase that says how to act or what to pick. Turning it up made the model write about what to say or what to do next, which fits the trigger reasonably well.

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

   our lives is to improve our experiences.⏎Improvement requires change, and change requires work. And with encompassing holistic changes, most people are challenged to know where to start.⏎In epistemology, the philosophical study of knowledge, “tabula

2. #2 peak

   including health insurance.⏎This is a guest post by Murray Newlands, the CEO and Founder of Influence People. Influence People<|endoftext|>It can be challenging to know what to do to get your middle school child ready for all of the activities, requirements and

3. #3 peak

   because we dont have the ability to handle truth. Truth is to much or to bright for us because it can be interpreted wrongly, and we wouldnt know what to do with it either.,⏎5. Lines 5 and 6 provide an example

4. #4 peak

   your application and see how prepared you are for college courses. Understanding the timing breakdown of the SAT and ACT will help you practice under realistic testing conditions and know what to expect on test day. Understanding how your scores are

5. #5 peak

   So, it should be inevitable that companies start making headway towards bringing a revolutionary technology out of the hospitals and into the markets.⏎It’s hard to know what to call a device that would

6. #6 peak

   library supports. Invoking the tag library imports custom processing and actions into the Java environment so a Java runtime environment like JRun 3.0 will know what to do with such tags as they're recognized. Tag libraries are usually packaged as Java

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

   ideas you'd like to contribute, we'd love to hear from you.⏎Find the latest in professional publications, learn new techniques and strategies, and find out how you can connect with other literacy professionals.⏎Teacher Resources by Grade⏎|1st -

2. #2 peak

   loose with our terms, but that just makes it more confusing.⏎You ought to be able to think these through - take a shot and we'll tell you where you're on and off-target.⏎Ok, thats a good idea.⏎1. Unfortunately

3. #3 peak

   given/known data If an athlete jumped 2 feet high and left the ground at an angle of 20 degrees with respect to the horizontal, how fast was the athlete going in the forward (positive horizontal) and upward (positive vertical)

4. #4 peak

   ideas you'd like to contribute, we'd love to hear from you.⏎Find the latest in professional publications, learn new techniques and strategies, and find out how you can connect with other literacy professionals.⏎Teacher Resources by Grade⏎|1st -

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.