'domain' after time or frequency

What this neuron does

This neuron lights up on the word 'domain' or 'waveform' when it follows words like 'time', 'frequency', or 'wave'. Turning it up made the model write about signals and waveforms, like a time domain signal.

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

   those two sensors. Two common techniques to estimate the spatial coherence for narrowband S-MMG signals, namely the magnitude squared coherence function and the maximum of the time-domain cross-correlation function, were found to yield similar results. In particular, high

2. #2 peak

   NMRView involves visualizing and analyzing NMR spectra. Many users of NMRView will use other programs to transform the original time domain data into the frequency domain. Since there is no standard data format for NMR spectra that is in common

3. #3 peak

   MRI techniques, OCT uses light waves for imaging. The shorter wavelength of light empowers this technology to generate high-resolution, cross-sectional images with zero delays.⏎Time Domain technology was the first method that was used in OCT technology. Time Domain technology uses

4. #4 peak

   2. However, owing to its advantages and usability over other imaging technologies such as Spectral-Domain Optical Coherence Tomography (SD-OCT) and Time Domain Optical Coherence Tomography (TD-OCT), it becomes a superior retinal

5. #5 peak

   voltage drop waveforms are in-phase with each other.⏎Given that the power supply frequency is 6

6. #6 peak

   19, De Forest filed the first patent on his phonofilm process. This enabled the recording of sound in electrical waveforms which can be translated back into sound waves when the movie was projected. The first

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

   remains unchanged during physical processes. With respect to classical physics, conservation laws include conservation of energy, mass (or matter), linear momentum, angular momentum, and electric charge. With respect to particle physics, particles cannot be created or destroyed except in pairs

2. #2 peak

   conservation of electric charge. There are also many approximate conservation laws, which apply to such quantities as mass

3. #3 peak

   0 degrees C).⏎Electrostatic spark discharge results from the internal molecular friction that generates high-voltage electric charges such as where oil passes through very tight clearances at high flow rates, producing

4. #4 peak

   ions of the day, and besides, if you could have a successful theory that didn’t have to introduce some new particles that were themselves sketchy (their electric charges had to be fractions of the electron charge, and they apparently couldn’t be observed

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.