line breaks inside wrapped sentences

What this neuron does

This neuron reacts to a line break that falls in the middle of a sentence, which is what happens when text was copied from a page with fixed-width lines. It does not seem to care about the meaning of the words. Turning it up did not produce any clear theme in the model's writing.

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

   in 1957. Among the many admirers of Strong were⏎Sir James Lorimer (St. Kilda Cemetery), Alfred Felton (St.⏎Kilda Cemetery) of “Felton, Grimwade & Co”, and

2. #2 peak

   for pilgrims and visitors from its home country. Moreover,⏎the hostels were used for meetings, dining and other social activities.⏎Shortly after the Order of St.⏎John had arrived in Malta in 1530, each langue started to

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

   ’s⏎issue of The CampLine,ACA has written about the most current information⏎available concerning the issue.1 Will it ever end, you might⏎ask? In reality, as long as there are vehicular accidents involving children⏎

5. #5 peak

   etween generations, particle differ by their quantum number and mass). The first generation consist of the electron (e−⏎) and electron-neutrino (νe⏎). The second generation consist of the muon (μ−⏎) and mu

6. #6 peak

   waZulu-Natal and the Eastern Cape. It prefers woodland dominated⏎by a broad-leaved trees such as bushwillows (Combretum), Silver⏎cluster-leaf (Terminalia sericea), Burkea (Burkea afr

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

   Spain; France;⏎United Kingdom; Isreal; Lebanon; CIS=Russia (Siberia); Myanmar (formerly Burma); Japan;⏎- Tertiary/65-2 mya: Sweden; Poland; Germany

2. #2 peak

   York,⏎Delaware, North Carolina, Tennessee, Arkansas, South Dakota, Nebraska,⏎Kansas, Texas, New Mexico, Montana, Alaska, and California; Canada=⏎Manitoba, Alberta, British Columbia; Mexico; Brazil; Poland; Denmark

3. #3 peak

   >>> len("a string") 8 >>> >>> s = "a long string" >>> >>> len(s) 13 >>> >>> len("") 0 >>>⏎>>> >>> s3 = '' # empty string using single quotes >>> s3 ''

4. #4 peak

   and⏎African American History -⏎This website is for African American Artists and an on-line portal⏎for both African America Artists and African American History. The website⏎contains 1000's of links and 100's 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.