end of a short definition or claim

What this neuron does

This neuron lights up at the full stop or line break that closes a short statement, especially a dictionary-style definition or a bulleted fact, just before a new item starts. Turning it up made the replies repeat or wander, so it does not tell us much more.

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

   powers.⏎- A public land surveying unit of 36 sections or 36 square miles.⏎- An ancient administrative division of a large parish in England.⏎- A racially segregated area in South Africa established by the government as a residence for

2. #2 peak

   . All rights reserved.⏎- n. a region in northmost Europe inhabited by Lapps⏎Sorry, no etymologies found.⏎Subfossil samples of Scots pine Pin

3. #3 peak

   ?⏎Consider these alternate headlines:⏎- “Icy conditions take clueless drivers by surprise”;⏎- “Too many crashes caused by overdriving winter road conditions”; and⏎- “Drivers fail to slow down in slippery conditions; no wonder IC

4. #4 peak

   million Americans had received their COVID-19 shots, there were 3,544 reported deaths following COVID vaccination, or about 30 per day⏎- In just four months, the COVID-19 vaccines have killed more people

5. #5 peak

   rotechny, imparting an intense red color to flames.⏎- n. A metallic chemical element (symbol Sr) with an atomic number of 38.⏎GNU Webster's 1913⏎- n. (Chem.) A

6. #6 peak

   is not common but is still a risk that needs to be managed Some businesses have had unsafe work practices for many years before they have a fire caused by spontaneous ignition.⏎The possibility of spontaneous ignition is greater if the surrounding air is warm and dry –

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

   211171, China⏎2 Nanjing Xiaozhuang University, Nanjing, Jiangsu 211171, China⏎*Authors to whom correspondence should be addressed.⏎Received: 2020

2. #2 peak

   To access this title, visit your library in the app or on the desktop website.⏎Chronicles of the imagination Geographical⏎- Walta Evans "School Librarian

3. #3 peak

   is a free software. We also strongly recommend that you sign up for an AdobeID at the Adobe website. For more details please see FAQ 1&2. To view this ebook

4. #4 peak

   line.com/VECE20|⏎|Order Information:||Web: http://www.tandfonline.com/pricing/journal/VECE20|⏎When requesting a correction, please mention this item's handle: RePEc:

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.