word pieces inside names

What this neuron does

This neuron fires on the middle pieces of names split into several parts, such as the "gen" in Röntgen or the "ux" in Benelux. The steering results did not show a clear theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

   but the 8th November actually marks 115 years since the X-Ray was first invented. The honor goes to German physics professor Wilhelm Röntgen who discovered the use of an X-Ray way back in 1895

2. #2 peak

   . However, Humberto may later regenerate into a tropical cyclone as it moves over warmer water and away from the wind shear.⏎The Moderate Resolution Imaging Spectroradiometer (MODIS) aboard NASA’s Aqua satellite captured this true-color image of

3. #3 peak

   Antalya-Türkiye’de doğdu. Lisans öğrenimini MSÜ Den

4. #4 peak

   , in recent years, to constitutional amendments granting these regions formal recognition and autonomy.⏎In 1948 Belgium became a co-signatory to the Benelux Customs Union along with the Netherlands and Luxembourg. This later became the Benelux

5. #5 peak

   to display her beauty to the people and the nobles, for she was lovely to look at.⏎As the story continues, pride creeps in.⏎Xerxes wanted to show off his beautiful wife! But it seems as though he didn’t

6. #6 peak

   without the patient actually being cut open!⏎The discovery of x-rays was a happy accident. A physics professor named Wilhelm Roentgen was testing whether cathode rays could pass through glass and observed a mysterious light that

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

   our du.⏎- Our du is 5 -- let me circle that and let me do that in that blue color --⏎- is 5 cosine of 5x dx. So we can rewrite this entire expression as --⏎

2. #2 peak

   you look over here, we don't have quite du there. We have just cosine of 5x dx--⏎- sorry, I need cosine of 5x dx, just like that. So when you look over here,⏎- you have

3. #3 peak

   the commands you give and the M-file are somewhat disparate. The process is illustrated using a single, simple differential equation:⏎Integrate this equation from t = 0 to t = 1. The exact solution can be found by

4. #4 peak

   let's think about whether u-substitution might be appropriate. Your first temptation might to said,⏎- "Hey, maybe we let u equal sine of 5x, and if u is equal to sine of 5x,⏎- we have

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.