chemistry name endings like ether and ketone

What this neuron does

This neuron fires on the endings of chemical names, such as 'ether', 'ethers', 'ketones', 'ketamine' and 'aldolase'. It goes strongly negative on words like 'wise' and 'smart' in advice sentences, such as 'be wise'. Turning it up or down gave text that did not clearly relate to chemistry, so the steering results don't confirm the pattern.

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

   osis. Your healthcare team may ask you to check for ketones, especially if you have type 1 diabetes.⏎When to check for ketones⏎Ketones in your blood or urine mean that you don’t have enough insulin in your body

2. #2 peak

   codeine. Examples of POPs are mercury, fire retardants (polybrominated diphenyl ether or PBDE), and poly-chlorinated biphenyl (PCB).

3. #3 peak

   that are stitched together with some sort of linking group. That can be as simple as a long alkyl chain, or a short stretch of ethylene glycol ethers, up to as complex a linker as you have the patience to search for.⏎

4. #4 peak

   formation of a greater number of aromatic compounds and ethers during distillation (60–100% more than stainless steel apparatus

5. #5 peak

   in mixtures; specifically, 2 or more compounds were found in about one quarter of the sampled urban wells.⏎A commonly detected VOC is methyl tert-butyl ether (MTBE), which is a gasoline oxygenate designed to add oxygen to decrease

6. #6 peak

   according to the U.S. Drug Enforcement Administration (DEA).⏎Ketamine Found Effective, but More Study Suggested⏎The researchers found that ketamine

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

   to protect someone or something.⏎From St George to George the dragon-slayer⏎Consequently, although St George is no longer a saint, it may be unwise to dismiss him altogether. Formerly a saint, George is now mythic.

2. #2 peak

   It means we’ll have to shift food production, migrate crop production to other parts of the world to keep it up. Given all these pressures, we should be smart about how we use our resources — and one of our resources is soil.”⏎Brad

3. #3 peak

   good sign. Chemicals like arsenic are then released, and these build up as residue in the bottle, mixing in the water that ultimately YOU drink.⏎Be wise, and ditch plastic bottles, especially for the health of your family. It is

4. #4 peak

   education is the key not only to personal prosperity but to civic virtue and harmony. “Wisdom's ways are ways of pleasantness and all her paths are peace,” he quoted

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.