period after 'Dr' abbreviation

What this neuron does

This neuron fires on the full stop in 'Dr.' when it comes before a person's name, as in news articles about doctors. Its negative side appears inside programming identifiers, but steering it did not change the writing in an obvious 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

   , including the germs that cause cholera and other diarrheal illnesses.⏎Data now suggest that the locations where certain pathogens are found have changed, said Dr. Glenn Morris, the director of the Emerging Pathogens Institute at the University of Florida

2. #2 peak

   13 Desktop News | Troubled youth in the custody of the Alabama Department of Youth Services have been given a second chance at success thanks to the work of Dr. Randy Salekin, a professor in the Department of Psychology

3. #3 peak

   10 percent of those people surveyed - including physical therapists, speech and hearing therapists and social workers - were confident in their training in these issues. According to Dr. E. Virginia Laph

4. #4 peak

   breathalyzer that can test people for COVID-19.⏎The test identifies the disease within 15 seconds. The standard PCR test can take days.⏎Dr. Pelagia-Irene (Perena) Gouma, professor

5. #5 peak

   be increasingly common -- because evolution's "survival-of-the-fittest" theory should dictate that we'd lose such disabling traits.⏎But an analysis by Dr. Atul Butte and graduate student Erik Corona of Stanford University's School of Medicine

6. #6 peak

   , the grants are designed to help institutions expand opportunities for student research projects.⏎"We're seeing a profound change in the way many college students learn science," said Dr. Joseph G. Perpich, the institute's vice president for grants and special

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

   typedef void * model_3d_ref;⏎model_3d_ref load_model_from_disk(const char * absolute_file_path);⏎void draw_model(model_3d_ref the_model, float

2. #2 peak

   where_x, float where_y, float where_z);⏎void deallocate_model(model_3d_ref kill_this);⏎The compiler doesn't read your code like this - the following

3. #3 peak

   as an int, but the function performs a byte per byte search using the unsigned char conversion of this value.⏎- Number of bytes to be analyzed.⏎sizet is an unsigned integral type.⏎A pointer to the first occurrence of value in the

4. #4 peak

   ⏎But here thing is, save() method can return that primary key id value which is generated by hibernate and we can see it by⏎long s = session.save(k);⏎In this same case, persist() will never give

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.