opening parenthesis after a term

What this neuron does

This neuron lights up on an opening bracket "(" that starts a side note, such as an abbreviation, a label or a definition placed right after a word. When it was turned down, the model started writing lists of numbered brackets like "(a) (b) (c)", but turning it up made the text drift into ordinary prose.

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

   and the motionless move. Cochlear implants have been an unprecedented success in biomedical engineering (1) and may only be surpassed by the visual implants currently in development (2). The first tetraplegics with implants allowing them to move robotic

2. #2 peak

   (1) is the curved bottom part of the nail. The mottled light and dark tissue (2) is the top part of the nail.⏎As you cut the nail deeper

3. #3 peak

   be broken using mechanical force and so the microLEDs can be easily separated from the substrate and transferred to the final backplane.<|endoftext|>Understanding Figurative Language (Part 2)⏎This is the second article addressing the matter of distinguishing between literal

4. #4 peak

   of mutations to improve their stability was carried out by Professor David Stuart and his team at Oxford University using Diamond Light Source, the UK's national<|endoftext|>Coronavirus (COVID-19) and travel: The situation around the world is changing dramatically

5. #5 peak

   .⏎Because the University places a high value on academic honesty, penalties for mistakes and violations are severe.⏎How new technology helps detect cheating and plagiarism⏎The answer sheets (scantrons) used for most multiple choice exams are processed by a program called

6. #6 peak

   integrated, engineering-level computer code that models the progression of severe accidents in light water reactor nuclear power plants. MELCOR is being developed at Sandia National Laboratories (

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 graph has 4 vertices and the following relations exist (1,2), (1,4) and (2,3). Then the table would look

2. #2 peak

   . Click and begin.⏎GCF and LCM by Prime Factorization⏎A straight forward way to find the greatest common factor (GCF) and least common multiple (LCM) using prime factorization. Article includes examples

3. #3 peak

   斯羅 (사라, Sara), 徐那(伐) (서나[벌], Seona[beol]), 徐耶(伐) (서야[벌], Seoya[beol]), 徐羅(

4. #4 peak

   is a series of cross sections of anatomical structure. In most atlases, the three dimensions are as latero-lateral (x), dorso-ventral (y) and rostro-caudal (z). Another one is a

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.