opening parenthesis after a bracket or name

What this neuron does

This neuron reacts weakly to an opening bracket that follows a closing bracket, a name, or a date, as in citations and reference lists. The signal is small, and turning it up did not produce a clear change in the writing.

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

   ) (50-item version 7.0 ESL/EFL) of R. L

2. #2 peak

   ed.) (1981). Modern Physics and Problems of Knowledge. Open University Press.⏎

3. #3 peak

   outlet of Barombi Mbo) (Ref. 4999), in west Cameroon.⏎Size / Weight /

4. #4 peak

   = dF(x)/dx = (dF(x)/dx2)(dx2/dx) = 2x (dF(x)/dx2) (1)⏎When you differentiate the integral with variable upper limit it gives you the function

5. #5 peak

   Silla (57 BC[note 1] – 935 AD) (Korean pronunciation: [ɕʰilːa]) was one of the Three

6. #6 peak

   5) is a multicomponent compression system which ensures reliable and continuous compression that patients need to recover from their venous leg ulcer (4) (6) (7).⏎(1) Posnett, J., Gottrup, F.,

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

   ) 2020 rankings, Pakistan ranked 154th among 1

2. #2 peak

   ) of each test. They cover the same material, but have been reorganized to allow

3. #3 peak

   ) to help educate our patients on the signs and symptoms of gum disease and how to treat

4. #4 peak

   ) to assume several births simultaneously.⏎The philosophy of pariśeṣanyāya or

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.