"more" after verbs like 'find out'

What this neuron does

Fires on the word "more" in calls to action like "Find out more" or "Learn more." The effect is weak. Its strongest negative cases are the word "buffer" in technical text about Emacs markers. Turning it up gave off-topic 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

   an invaluable guide to⏎Find out more⏎Creek Books is a⏎small publisher committed to "teaching kids to

2. #2 peak

   like goldenrod are bumble bee magnets. So are herbs including lavendar, anise hyssop, motherwort, basil and sage.⏎Want to see more flowers -- and herbs to help bees? Check out this

3. #3 peak

   2<|endoftext|>David Bourget (Western Ontario)⏎David Chalmers (ANU, NYU)⏎Rafael De Clercq⏎Jack Alan Reynolds⏎Learn more about PhilPapers⏎OUP Oxford (2011)⏎With more

4. #4 peak

   , and managing some of the practical things, such as getting the right shoes or working with a personal trainer.⏎This guide’s main goal is to help you become more active, get the most from your activities, and do them safely. The key

5. #5 peak

   track of books you want to read. Want to Read saving…. Want to Read Currently Reading Read. Other editions. Enlarge cover. Error rating book.⏎Browse more videos⏎Human Anatomy and Physiology are two most-related subjects in the field of medical

6. #6 peak

   . It’s made to help everyone from brand new hobbyists to university Geology students, and includes an eBook, digital tools, a video tutorials. Find out more here!⏎While all obsidian meets this

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

   make-marker)) ⇒ #<marker in no buffer>⏎m1to point between the 99th and 100th characters ;; in the current buffer: (set-marker m1 1

2. #2 peak

   00) ⇒ #<marker at 100 in markers.texi>⏎;; Now insert one character at the beginning of the buffer: (goto-char (point-min)) ⇒ 1 (insert "Q")

3. #3 peak

   ’s insertion⏎type (see Marker Insertion Types)—unless the insertion is done⏎insert-before-markers (see Insertion).⏎Insertion and deletion in a buffer must check all the markers and relocate them if necessary. This slows processing in a

4. #4 peak

   position in that buffer. But the marker’s position value can change during the life of the marker, and often does. Insertion and deletion of text in the buffer relocate the marker. The idea is that a marker positioned between two characters remains between

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.