opening parenthesis after a noun phrase

What this neuron does

This neuron fires on an opening bracket that starts an aside, like a clarifying note or a number in brackets after a noun. Turning it up produced text that drifted into odd, repetitive wording rather than anything tied to brackets.

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

   is feasible to ask whether crocodilian species may also harbor the influenza A virus. Here we analyzed 37 captive crocodilians from two locations in Florida (plus 5 wild bird fecal samples from their habitat) to detect the presence

2. #2 peak

   studies investigated when children became able to detect that the words of a story could support multiple interpretations. Each subject saw two eight-sentence stories of each of four types (no-cause, unbiased, biased-proximal, and biased-distal),

3. #3 peak

   (24 in English; 24 in French in the French part) include an audio description for the blind and visually impaired; and 49 films (27 in English; 22

4. #4 peak

   biology), and figuring out how to save everything (conservation biology). Further, when elements cannot be saved, field biologists help bring back species and their ecosystems (restoration biology).⏎Chicago Scholarship Online requires a subscription or purchase to access the full

5. #5 peak

   the different types of relationships on the board.⏎Activity One: My Own Square Meter (30 minutes)⏎1. Have students go outside and pick a small area (about a square meter each) to explore. It is preferable that this

6. #6 peak

   find targets for better treatments. It’s latest in a steady stream of good news from autism researchers recently, who have reported on innovative ways to diagnose the disorder earlier (as we reported here, here and here) and on new genes that contribute to

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

   individual battery voltages are added together. When charging your battery, it is necessary to account for the total voltage of the string.⏎For example, if you have (2) 100 amp hour, 6 volt batteries connected in series

2. #2 peak

   me about 2nd conditionals, but I'm a safe bet for what reads well in (American) English.⏎Me too. I think the 'brass' refers to

3. #3 peak

   there are also (possible) cases of justified aversions/downplays: ie heart surgeon, firefighter,

4. #4 peak

   perform ... such as shuffling a deck of cards. Remember this next time you play!⏎[I apologise that (during the video), when writing the huge numeral above, I inadvertently wrote part 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.