'that' in 'so that' purpose clauses

What this neuron does

This neuron lights up on the word 'that' when it follows 'so' to mean 'in order that', as in 'arrange them so that they made sense'. Turning it up did not make the model write about purposes or goals; its replies just wandered.

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

   then you are done. b. If you get , then you have to algebraically manipulate your function so that you can use direct substitution: i. Factoring ii. Rationalizing (Rad

2. #2 peak

   , model year numbers (cars), and other useful numbers there. Once they had their numbers, they needed to arrange them on the paper so that they made sense (no dividing by zero) and so that they can be solved

3. #3 peak

   a carpenter's square.⏎Find the area of the shaded region created by the two overlapping⏎triangles in terms of a and b?⏎Position the lines so that they are perpendicular to each other.⏎What can you say about the equations of perpendicular

4. #4 peak

   and don’t forget to limit the amount of them per day.⏎When the animals are first fed with strawberries, you should consider a small amount before leveling up so that their stomach can get used to it. Their digestive system is so sensitive that it

5. #5 peak

   pieces, it is possible to fit the pieces together again to make a new shape. How many new shapes can you make?⏎Can you shunt the trucks so that the Cattle truck and the Sheep⏎truck change places and the Engine is back

6. #6 peak

   . Using the rules, where⏎are they all sitting? Can you find all the possible ways?⏎What is the best way to shunt these carriages so that each train⏎can continue its journey?⏎If you split the square into these

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 less ornamented, laid over the saddle or furniture of a horse, especially of a sumpter-horse or horse of state.⏎- Clothing, especially sumptuous clothing; equipment; outfit.⏎- To cover with a caparison,

2. #2 peak

   me, but it never lasts longer than five minutes (32).⏎6: Correct Usage 7 | Mind you, the spare room is pretty sumptuous too; in fact, I think he gets his own Jacuzzi, so

3. #3 peak

   have strep throat. The cause of these signs and symptoms could be a viral infection or some other illness. That's why your doctor generally tests specifically for strep throat.⏎It's also possible for you to be exposed to a person who carries

4. #4 peak

   6: William Faulkner's Absalom, Absalom!,⏎1938: John Dos Passos's U.S.A. trilogy,⏎19<|endoftext|>A view can become a page

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.