'is' after a long subject phrase

What this neuron does

This neuron fires on the small word 'is' (or 's) that comes right after a long subject, as in 'Making sure your soil is... is important' or 'Interesting fact is that'. When turned up, the model got stuck repeating 'is' or 'was' over and over.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

   ability to bring in subtle elements, to pause and consider is vital for their patient.⏎We now have artificial intelligence which can replicate part of the

2. #2 peak

   returns, you collect and analyze the information gathered by the instruments you designed. This information is pivotal in gaining a clearer picture of how the aircraft is functioning.⏎This is a job that requires an acute attention to detail. Test flights are

3. #3 peak

   got a newsletter from the unmanned-vehicles industry about all the cool things robots are doing to help Japan. It has not a word about the nuclear reactors. That's disgraceful.⏎To head off the next nuclear accident, we need to rethink the

4. #4 peak

   were discovered in this isolated location, such as:⏎The mountain acts like an island in the vast sea of jungle, isolating the wildlife on it. Interesting fact is that most wildlife living in the Bosavi Crater show little to no fear of

5. #5 peak

   robot to take home with them! For kids entering 2nd-6th grade in fall 2021.<|endoftext|>Create your own garden at home is not easy. Therefore, many people who entrust the construction of gardens on expert

6. #6 peak

   pests, and watering your garden more natural and sustainable.⏎Making sure you build your soil so that your crops get adequate nutrients is important—and you can definitely accomplish this goal without buying anything in a package or a

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

   do not require the last check, but none of real⏎"I have come to believe that the whole world is an enigma, a harmless enigma⏎that is made terrible by our own mad attempt to interpret it as though it had⏎an

2. #2 peak

   women who weigh more or who exercise regularly.⏎Very low calorie diets of fewer than 800 calories per day should not be used unless you are being monitored by your doctor.⏎Healthy Weight Tip⏎Set goals to eat healthy like

3. #3 peak

   feeling secure gives children the confidence they need to explore, learn and take on the world!⏎Talk, Sing and Point⏎Babies learn language from the moment they are born. To a newborn baby, speech is just sound. Then, day by

4. #4 peak

   Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be more creative & energetic with your students!⏎Students participate in a variety of physical activities

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.