line break inside wrapped text

What this neuron does

This neuron fires on a line break that splits a sentence in the middle, the kind found in emails, forum replies and text that was wrapped to a fixed width. Turning it down made the model produce list-like lines, and turning it up gave loose, repetitive prose.

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

   22:12:37, Russ Abbott wrote:⏎> Cool. I wasn't aware of that notation. It doesn't quite get to the⏎> issue though.⏎> The problem I'm concerned about is the need to define

2. #2 peak

   , and there may be nothing about var11 . var1 $ x that⏎> changed, etc. Yet one is apparently forced to keep track of and⏎> reconstruct all those elements.⏎The compiler takes care of that.⏎> Another example

3. #3 peak

   set in motion,<|endoftext|>The Edgar Cayce health information is a rich source of research hypotheses⏎with regard to anatomy, physiology, pathology, and therapy. This⏎section contains a variety of research hypotheses waiting to be pursued.⏎If you have expertise

4. #4 peak

   http://en.wikipedia.org/wiki/Analysis_of_algorithms)⏎> 1 get a positive integer from input⏎> 2 if n> 10⏎> 3 print "This might take a while..."⏎> 4 for i =

5. #5 peak

   is a moveable point on the hypotenuse, and P and Q are the feet⏎of the perpendiculars from X to the sides of a right angled⏎triangle. What position of X makes the length of PQ a minimum?⏎The circum

6. #6 peak

   early through its center; by Mad and White Rivers; and by Lake Champlain,⏎which affords it many navigable privileges. The soil is good, particularly⏎in those towns below the mountains, and bordering the lake<|endoftext|>“ The L

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

   times of several years. The total energy radiated in a superburst is 1042 erg. Superbursts<|endoftext|>Kang, T-J. (2018) Online learning in North Korea The Diplomat, May

2. #2 peak

   conuts and banana leaves<|endoftext|>const void * memchr ( const void * ptr, int value, size_t num );⏎void * memchr ( void * ptr,

3. #3 peak

   Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the page “GNU Free Documentation License”.⏎The copyright and license notices on this

4. #4 peak

   0.1016/j.jbusres.2013.10.001⏎BERISHA-NAMANI, M. (2013). Information technology, internet, and marketing. International Journal 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.