'who' after a name and title

What this neuron does

This neuron fires on the word "who" when it comes right after a person's name and job title, as in "said psychologist Jack van Honk, who led the study". It is about linking a named expert to a description of what they did. Turning it up did not change the writing in a clear way.

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

   ins.⏎The new findings add to the scientific heft underlying acupuncture, said neuroscientist Maiken Nedergaard, M.D., D.M.Sc., who led the research. Her team is presenting the work this week at a scientific meeting

2. #2 peak

   what interesting and unique birds call the site home or have stopped by on their way south.⏎According to LyondellBasell Senior Vice President Dale Friedrichs, who has participated in most of the Matagorda counts, there are three elements of

3. #3 peak

   an environmental influence that has magnified effects on some minority children at lower-income urban schools,” said Dr. Brennan Davis, assistant professor of marketing at Baylor University, who co-authored the study with Dr. Sonya Grier, associate professor of marketing

4. #4 peak

   bracelet and brooch fragments and other objects that would have been highly prized objects.⏎Dr Gordon Noble, Senior Lecturer, Department of Archaeology, University of Aberdeen who led the

5. #5 peak

   confidence in others.⏎“Testosterone reduces trust just enough to make people vigilant and careful,” said psychologist Jack van Honk of Utrecht University in the Netherlands, who led the study published May 24 in* Proceedings of the National Academy of

6. #6 peak

   masses billions of times the mass of the sun could exist so early in the history of the universe,” astronomer Julie Comerford of University of California Berkeley, who was not involved in the study, wrote in an e-mail to Wired.com.

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

   data, we think this problem is relevant for Professor Finnegan's class at WSU.⏎What textbook is this problem found in?⏎Our data indicates that this problem or a close variation was asked in Chemistry: An Atoms First Approach - Zumd

2. #2 peak

   problem of the brash young Texan and referred him to a couple of recent Caltech graduates, Howard Lewis and Bruce Burns.⏎Howard contacted the two engineers, and they were

3. #3 peak

   manager from this point to ensure the employee’s contributions are valued and that their needs in knowing how to do their job are<|endoftext|>No person shall hold any civil office unless that person be a qualified elector for such office. Article IX, Section

4. #4 peak

   5 mg/kg, 5 times daily for 5 days.⏎Best of luck---⏎Search for questions⏎Still looking for answers? Try searching for what you seek or ask your own question.⏎Posted 31 Aug 2009 •

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.