line breaks inside wrapped sentences

What this neuron does

The neuron fires on the invisible line break that a text has partway through a sentence, where the line was wrapped by a page or column rather than ending a thought. Turning it up did not make the writing look or read differently in any clear 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

   -splicing and in some cases can act⏎as an enzyme. A wide variety of rRNA molecules and some mRNA molecules (chloroplast and mitochondrial) can splice⏎themselves. These molecules are called ribozymes (RNA enzymes; Figure

2. #2 peak

   areas mark⏎seismically active regions in the channel between Fogo and Brava (seismic crisis 1994) and at Cadamosto⏎seamount (Heleno et al 1999; Grev

3. #3 peak

   the double⏎helix is said to "melt" into its two component molecules, and will⏎reassociate upon slow cooling under appropriate salt conditions. So,⏎the issue is not decomposition so much as disassociation upon exposure⏎to too high

4. #4 peak

   to specify, visualise,⏎construct and document the artifacts of an object-oriented software-intensive⏎system under development. The UML represents a compilation of "best engineering⏎practices" which have proven successful in modelling large, complex systems.⏎UML

5. #5 peak

   race for a cure holds a promise for many struggling with the disease.⏎Eight million people die from cancer worldwide every year, out of which four million people die prematurely⏎(aged 30 to 69 years). Leading cancer risk factors include

6. #6 peak

   works. Normally when you try and cd⏎into a directory, it will only try and change to the path specified from the current directory. If you spend a⏎lot of time working in specific folders, it might be useful to assume that your

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

   that the foe, or their progenitors,⏎had been citizens of Colordo in the far West. And that,⏎having conquered all before them, they sought another⏎World to conquer here.⏎When we do trace out nature's laws,⏎And view

2. #2 peak

   bars,⏎When, oh! the welcome news then came,⏎To get abound the cars.⏎They marched us through their nasty streets,⏎That all the crowd might see,⏎The “hiding Yankees” from the North,⏎That in than land run free

3. #3 peak

   two or more servers do not interfere⏎with each other. Usually NFS file locking is handled by the⏎lockd daemon, but at the moment there is no⏎platform that performs locking 100% reliably in every situation.⏎With this

4. #4 peak

   ) Tetragonal System :⏎Three axes make right⏎angles with each other. The two horizontal⏎axes, a and b, are of equal length but the⏎third, c axis, is of different length, e.g⏎(iii)

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.