'that' after a thing being defined

What this neuron does

This neuron fires on the word "that" right after a noun that is being described, as in "a server-side scripting language that..." or "a computer code that...". It is a signal that a description is about to follow. Turning it up did not give a clear, consistent change in the output.

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

   every databases – MySQL, ORACLE, PostgreSQL, Sybase, Informix to name a few.⏎What is PHP?⏎- PHP is a server-side scripting language that means its code is executed on

2. #2 peak

   ynthesis.⏎Both tree species showed significant drought effects<|endoftext|>Introduction to Kubernetes⏎Kubernetes, also known as K8s or Kube, is an open-source system that helps organizations manage cloud-based containerized applications. The system helps with

3. #3 peak

   Regional Broadband Global Area Network (RBGAN) mean?⏎Regional broadband global area network (RBGAN) is a now-defunct IP-based, shared carrier service that was offered on a regional basis. The service was provided by network mobile satellite company

4. #4 peak

   we be willing to change who we are and how we behave in order to meet the expectations of those around us?⏎Summary: Animal Behaviour is an animated short film that centres around a group therapy session attended by animals, who are attempting to overcome their

5. #5 peak

   alin. Amygdalin is a chemical ingredient found in the pits of many fruits, raw nuts, and plants (see Question

6. #6 peak

   identified in several microorganisms. In these cases the self-assembly of the protein is advantageous to the organism. For example, hydrophobins are fungal proteins that self-assemble in an ordered manner into amphipathic films at air:

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

   .⏎Edmund was educated at Wakefield Grammar School and University College, Oxford. He became a fellow of Magdalen College and while there, made a name for himself as a

2. #2 peak

   , is stranger: they became symbols.⏎There is a single species of palm native to the entire state of California, the California fan palm, which is a big one with what looks like a fuzzy beard of brown leaves underneath its green fronds.

3. #3 peak

   it, including the numerous myths and confusing science that pervade the online world.⏎Strauss is a distinguished professor in the Oregon State College of Forestry and a fellow

4. #4 peak

   . Today, that number is 25 percent—still half the rate of the global average.1⏎Gayle Tzemach Lemmon, a senior fellow at the Council on Foreign Relations as well as a journalist and the best-selling author

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.