"above" after "the" pointing back

What this neuron does

This neuron fires on the word "above" when it follows "the" and points back to something already said, like "the above circuit diagram". Turning it up did not produce a clear change in the written text.

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

   various biological systems. It is postulated that NO plays a protective role by acting mainly on the interruption of free radicals formed under oxidative stress. Given the above, our objective is to evaluate the influence of NO in physiological responses of sugar cane

2. #2 peak

   , lines and other symbols should be used to show how different components are connected. This information is crucial for figuring out the operation of the circuit.⏎By following the above circuit diagram rules, you'll be

3. #3 peak

   .⏎Since the above three linkage movements are all rotary movements, but in fact, the linear movement is

4. #4 peak

   needed in the aluminum smelting process?⏎Aluminum and aluminum alloy melts contain a large amount of hydrogen, metal and non-metallic inclusions.⏎If the above harmful substances cannot be removed in time before casting, casting defects such as pores,

5. #5 peak

   on that one.<|endoftext|>Watch: 1929 Stock Market Crash and the Great Depression – Documentary [58:35 minutes]⏎After watching the above video and the relevant discussion in Special

6. #6 peak

   3d_ref kill_this);⏎The compiler doesn't read your code like this - the following code is exactly the same to a compiler:⏎As humans though, the above is a lot more like gibberish.⏎void * load_model_from_disk(const

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

   B), a private conservation organization that holds Rio Bravo in trust for the people of Belize. PfB integrates elements of sustainable forestry and natural product harvesting, ecotourism, and education into a single comprehensive long-term management plan. For a location

2. #2 peak

   Bartholomae translated as neck etc. of daevic beings (see DĒW), and mentioned manaoθrī- as the corresponding ahuric word (AirWb., cols. 530, 1

3. #3 peak

   - Lifestyle & Culture⏎Kenya’s population is made up of over 40 different ethnic groups each with their own individual language, luckily English and Swahili is spoken by many.⏎Kenyan Tribes & People⏎Kenya is built

4. #4 peak

   your chances in the no-holds-barred class, or on the roof.⏎Passengers were still pushing their way on board and trying to find somewhere to stow their endless boxes and bags of luggage when a bell clanged and we were off

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.