'kung' and name fragments mid-word

What this neuron does

This neuron responds to pieces of names and words that are split in the middle, most strongly the syllable 'Kung' in names like Kung Fu and Kung-chang. It mostly stays quiet on word fragments inside longer words such as 'subunit' and 'Unite'. Turning it up did not give a clear, consistent change in the text.

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

   Department maintains an⏎Observatory for teaching purposes. The Copernicus Observatory is located⏎on the Coral Gables Campus, on the roof of the⏎Ungar Computing<|endoftext|>Higher insulation R-values, higher U-value windows, and sealing your

2. #2 peak

   . On<|endoftext|>Anatoly Lunacharsky On Literature and Art 1909⏎The greatest of all

3. #3 peak

   What Others Are Reading Right Now.⏎How to Turn (Almost) Every Lady’s Head⏎Top female stylists share their favorite men’s looks.⏎10 Kung Fu Movies Every Man Should See⏎From the absolute classics to the<|endoftext|>(Nan

4. #4 peak

   ), where it is stated that his other name was Kung-chang (Puṇyaçrîka?), can be said almost to

5. #5 peak

   na) is most commonly known in the Chinese Buddhist literature by the name of Açvaghosha. But according⏎to his Life he was also called Kung-tê-jih (i.e., merit-sun; in Sanskrit,

6. #6 peak

   :Information Networks⏎Indigenous Websites: Opinion⏎Aborigines Milton- Ulladulla region⏎Produced in consultation with the Kupa Piti Kungka Tjuta, the Senior Aboriginal⏎Women from Coober Pedy

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

   made of four identical subunits with a range of dehydron flaws. Simpler organisms have globin molecules that accomplish the same job with just one subunit.⏎The authors stress that they are not arguing against natural selection as a process;

2. #2 peak

   that employs sample derived rRNA capture probes to remove rRNA from a metagenomic total RNA sample. To begin, both mosquito and microbial small and large subunit rRNA fragments are amplified from a metagenomic community DNA sample. Then,

3. #3 peak

   Health Organisation (WHO) to build, year-by-year, public awareness that tuberculosis remains an epidemic in much of the world. This year’s theme, “Unite to End TB”, highlights the need for a concerted effort by the TB research community

4. #4 peak

   Black families<|endoftext|>What are we learning?⏎Math: We will use place value to compare numbers.⏎Reading: We will be reviewing several concepts from Unit 3.⏎Phonics:which, night, wish, want, open,p

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.