"like" after "you'd" or "something"

What this neuron does

This neuron responds to the word "like" when it comes after phrases such as "you'd like" or "something like". Turning it up didn't produce an obvious change in what the model wrote about.

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

   knows more about his or her learning strategy than anyone else. So if you'd like to learn something about the best strategy to use when teaching your students to fly,

2. #2 peak

   prompt (or something similar). Under UNIX, the prompt is usually something like $, #, or %. This shell is a process and it belongs to you

3. #3 peak

   the beginning, then scrub to the end and hit “N” so it will only render the part you’d like to see.⏎You can create inverted alpha mattes on top of objects to effectively

4. #4 peak

   of the circle, and move the circle that you clone from up so it lines up with the top of the pipe beginning / end. You should now have something like this:⏎Note the extra part of the

5. #5 peak

   going to want to sometimes render your project to play it back and watch it. Instead of rendering the entire project you can scrub in the timeline to where you’d like it to render and hit “B” for

6. #6 peak

   say you pose a multiple-choice question for which there is no single correct answer but for which there are perhaps more justifiable answers and less justifiable answers. Something like “Which of the following motivations best explains so-and-so’s actions in such-and

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

   steps, the width of the steps, and the height of the steps. 3. The number of steps will depend on the height of your deck and the length of your staircase. 4.

2. #2 peak

   used depends on the condition being treated. Generally, most practitioners recommend 5 to 1

3. #3 peak

   also maintains the path_to_inst instance database.⏎Updates to the /dev and /devices directories in response to dynamic reconfiguration events or file system accesses are handled by devfsadmd, the daemon version of the devfsadm command. This daemon

4. #4 peak

   can "hash" to the same position. If this occurs, then a collision has happened. How do you handle the collision? Hashing also leads to lots

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.