'to' in 'to do with'

What this neuron does

This neuron fires on the word 'to' in phrases like 'has to do with' or 'nothing to do with'. Turning it down made the model output only the word 'to' over and over.

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

   <|endoftext|>Forget the batteries for a second, thats just one of a thousand analogies you could use to describe voltage/current and the reason that no current flows has nothing to do with the electro-chemical properties of batteries, its far simpler.⏎The easiest

2. #2 peak

   build a modest addition to its building for Sunday school classes. Despite the church demonstrating that the addition is critical to<|endoftext|>STEM and Wall Street⏎What does STEM have to do with Wall Street?⏎When you think about CAREERS on Wall Street, what

3. #3 peak

   by a single or multiple earthworks of massive proportions. Hillforts must have formed symbols of power within the landscape, while their function may have had as much to do with ostentation and display as defence. Pentre Camp comprises a sub

4. #4 peak

   carbon dioxide does. Methane gas (CH4) traps about 34 times more heat within the earth’s atmosphere.⏎So what does worm manure have to do with dog waste?⏎Well, dog waste is not just full of bacteria that

5. #5 peak

   using the disciplinary methods passed down by his father.⏎“I have always believed that the way my parents disciplined me has a great deal to do with the success I have enjoyed as a man,” Peterson said in a statement

6. #6 peak

   ictions like gambling, that have nothing to do with food. Tolerance is both a result and a cause of addictive behavior

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

   workable solution for polygonal transects remains elusive.⏎Keywords: Boundary overlap, Inclusion region, Reflection method, Transect configuration⏎- We recommend that you also print this page and attach it to the printout of the article

2. #2 peak

   , they will absorb more nutrients and end up a similar size as they would in their natural habitat.⏎But, of course, the idea of a bonsai tree is to produce a plant that looks

3. #3 peak

   has unique experiences with a unique home environment. Her current attitude is a by-product of her life experiences and the people around her. My advice to you is stop worrying about whether your teen’s attitude measures up to other teens’ attitude but

4. #4 peak

   invented thousands of years ago but stairs are a 13th century invention. Claude Stairs was working on the court of Count Of Flanders and his idea was laughed at when he first introduced it in 1208.⏎The idea

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.