'sp' in split words

What this neuron does

This neuron responds to the letters 'sp' when they start the second part of a word, such as 'spindles', 'spores' or 'splicing'. Turning it up made the model produce strings like 'lelelele', and turning it down made it repeat 'note' or 'novel'.

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

   windows with large, sharp corners. Other variations include the passionate style, Neoclassicism as well as the Baroque style. Gothic architecture usually includes columns and spindles as well as the main characteristic of the Gothic style is the use of

2. #2 peak

   the substrate from the environment. If the substrate is exposed to the corrosive environment, the substrate will become the anode and corrosion will be dramatically accelerated resulting in spalling of the coating. Sealing or impregnation the coating is recommended.

3. #3 peak

   by the inverter is the analog spindle, and the spindle driven by the servo motor is the servo spindle. Both can meet the control requirements of CNC machine tool spindles.⏎With the development of technology in the field of

4. #4 peak

   Tick Paralysis⏎|Spinose Ear Tick⏎|Peanut-shaped and covered with small spines⏎||Causes intense irritation, rubbing, and hair loss⏎|T

5. #5 peak

   hide. So, as the eel glides along, it emits a doublet or triplet. If there is a fish hiding nearby, then its body will spasm and the spasm will generate pressure waves in the water. Although the electric

6. #6 peak

   of exons, has been found to occur⏎in the primary transcripts of at least 40 different genes. By altering the pattern of exons that are spliced⏎together different proteins can arise<|endoftext|>Ratio Forum is back on June

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

   ⏎For over 30 years now, TNO has been gratefully taking advantage of this unique research platform to measure greenhouse gases and aerosols, such as particulate matter,⏎as well as to verify Dutch and European emissions. It is therefore

2. #2 peak

   in the body by sun exposure.⏎Nitric oxide is one of your body’s most important molecules for blood pressure health.⏎It relaxes the inner muscles of the circulatory system allowing blood to course smoothly.⏎And

3. #3 peak

   Computing and ICT teacher originally from the North East of England and working in East London.⏎Download or subscribe to this show at https://twit.tv/shows/triangulation.⏎Thanks to Cachefly for the bandwidth for this show.<|endoftext|>

4. #4 peak

   converters (incorporating ceramic substrates), which reduce nitrogen oxides (NOx), and DPFs, which reduce particulate matter (soot).⏎Of course, Corning's substrate and filter technologies

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.