space before a citation year

What this neuron does

This neuron fires in academic citations like '(Scholze et al., 2005)', on the gap right before the year, after the author's name. Turning it up made the model produce repeated filler and lists, so the steering does not show a clear link to citations.

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

   with the biological, chemical, and physical sciences, about one-fourth work on problems involving human decision making (Scholze et al., 2005).⏎In 2006, the second YSN

2. #2 peak

   creating dependency. Reminding people of their mortality tends to make them hold more closely to traditional culture (Pyszczynski, Solomon, & Greenberg, 2003); this has implications for mental health, and can also be

3. #3 peak

   that if I hit my thumb with a hammer I blame myself, not the hammer, but people often blame equally mechanical programs for user initiated errors. (Miller, 2004, p. 31).⏎Computer programs are just as

4. #4 peak

   While the case of Johnson v. California challenged the practice of segregating inmates by using race as a classification, the practice is still actively implemented (Robertson, 2006). Research indicates that many “…prison officials separate inmates into

5. #5 peak

   , in a national study, the more ACEs a respondent reported the poorer health, mental health and educational outcomes later in life. (Felitti et al., 1998).⏎In addition, the stress of chronic childhood trauma known as

6. #6 peak

   G investigators carried out landmark studies on the natural history of cervical cancer that firmly established HPV as the necessary cause of this malignancy (Schiffman et al., 1993, 2007). Their efforts laid the groundwork

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

   a<|endoftext|>- Enter a word for the dictionary definition.⏎From The Collaborative International Dictionary of English v.0.48:⏎Nectarine \Nec`tar*ine"\ (n

2. #2 peak

   in upwards of 150″ per year. Temperature varies little, with the average temperature near 82, and the humidity is always high.⏎Figure 2. Yum! After a hard days

3. #3 peak

   and for this reason its conversational style feels more like a series of fireside chats than a regular college textbook. Those radio broadcasts were highly acclaimed and won the 2007 Linguistics, Language,

4. #4 peak

   —used to introduce an additional statement about something that has already been mentioned. —used after a preposition to refer again to something that has already been mentioned. See the full definition for<|endoftext|>I have recently been re-reading two books I purchased

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.