full stops ending sentences

What this neuron does

This neuron responds to the full stop at the end of a sentence in plain informational writing, such as health, science or how-to text. When it was turned up, the model's text wandered into different subjects and did not show a clear pattern.

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

   as difficult to understand. This is compounded by the use of complex definitions and terminology. These complex definitions result from a need to categorise kidney diseases according to the way

2. #2 peak

   be used to add visual interest to an outfit. When choosing patterns, it is important to consider their scale and how they will work with other elements of your outfit. You can also mix and match patterns for a more eclectic look, but it is

3. #3 peak

   chances of winning. These scams are based on a misunderstanding of probability and random number generation.⏎In some countries, governments regulate and oversee the operation of lotteries. Some governments outlaw the practice altogether, while others endorse it to some extent and organize

4. #4 peak

   are often separated from their parents for long periods of time. This can make the bonding process more difficult. Finding ways to help parents and these infants bond better is important for everyone in the

5. #5 peak

   and break it down into small logical sections. No hydrochloric acid needed! If you still find it daunting, why not

6. #6 peak

   platform they are targeting, be it iOS or Android, and adapt their coding practices accordingly. They face the challenge of optimizing app performance, ensuring compatibility across multiple devices, and

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

   amps⏎On June 26, 1934, President Franklin D. Roosevelt signed the National Firearms Act of 1934 into law. The act placed a tax on the manufacture and transfer of certain firearms, with new

2. #2 peak

   BY-SA 4.0<|endoftext|>Announcing the Aerial Expedition⏎We are proud to announce The Ocean Cleanup’s next major research mission: the Aerial Expedition. In September and October 2016, we will conduct a series of

3. #3 peak

   this passage and the surrounding text, the only plausible interpretation of the harm principle is as follows: An individual may do as he pleases, as long as he does not believe that he is causing harm to others. That is Mill’s prescription for

4. #4 peak

   do this are controlled by special neuron bundles in the spinal cord. It is not quite clear how these central pattern generators know how quickly the legs are to be moved.⏎An international team working with scientists from Harvard University and the Max Planck Institute of

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.