unclear: 'Lorenz' and name fragments

What this neuron does

This neuron fires on the name Lorenz, especially the letter z at the end of it, and on pieces of other names and technical words. It's not clear what they have in common. Turning it up gave unrelated text.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

   do so, since an infinite degree of accuracy would be required to differentiate between initial values that lead to completely different outcomes.⏎In 1963, Lorenz introduced the concept of what became known as the Lorenz attractor in his seminal

2. #2 peak

   can produce complex, non-repeating patterns. The Lorenz attractor describes the conditions that make the system behave chaotically.⏎The equations that govern the Lorenz attractor are⏎Lorenz attractor with r = 28,

3. #3 peak

   by a set of differential equations, and each simulation had its own initial values. One day Lorenz ran the same simulation twice and to his surprise found that the two rounds resulted in

4. #4 peak

   often occurs in chaotic systems.⏎Lorenz is perhaps best known for coining the term butterfly effect. Whilst a professor at the Massachusetts Institute of Technology, Lorenz developed the concept that tiny effects in one part of a system can lead to big

5. #5 peak

   the Kano camp:⏎Some things you will learn how to do:⏎– Build a computer with easy step by step instructions⏎– Creat projects like Snake, Pong, Minecraft and more⏎– Utilize connected light kits where applicable⏎– Share

6. #6 peak

   of strange attractors (J.C. Sprott). Attractors with dueling symmetry (C.A. Reiter). A new feature in Hénon's map (M. Michelitsch, O.E. Rössler

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

   Indirect reciprocity is a social interaction in which one actor helps another and is then benefited by a third party. Gossip has also been identified by Robin Dunbar, an evolutionary biologist, as aiding social bonding in large groups.⏎The word is

2. #2 peak

   , attention should be paid to the characteristics of various nozzles. General water film no

3. #3 peak

   :<|endoftext|>Copyright © University of Cambridge. All rights reserved.⏎'Aim High' printed from http://nrich.maths.org/⏎Why do this problem?⏎offers the opportunity for a statistical investigation⏎

4. #4 peak

   in Washington, D. C. (Image via Zach Montellaro on Flickr, CC BY-NC-SA 2.0)⏎The two Supreme Court cases, Jones v. City 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.