'that' after 'the good news is'

What this neuron does

This neuron fires on the word "that" when it introduces a full statement after phrases like "the good news is that" or "keep in mind that". Turning it up made the model write repetitive, circular sentences.

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

   as well as eggs. Along with beta-carotene and vitamin A, They protect your eyes from ultraviolet rays.⏎Keep in mind that your body needs a bit of healthy fat to best absorb these eye-benefitting

2. #2 peak

   Shalgi, PhD, a professor at Technion Israel Institute of Technology and the study’s principal investigator, said in a press release.⏎“The good news is that since the ability is there, we hope future treatments can be developed to activate it

3. #3 peak

   THMs). . Chloroform is an example of these TTHM’s. Some of these are either known or believed carcinogens.⏎The good news is that removing chlorine/chloramine also reduces TTHM’s, insecticides, pesticides

4. #4 peak

   research interest in healthy ageing, I find that I am always being asked for tips on lifestyle steps to stay well for as long as possible. The good news is that it is never too late to take make changes to improve wellbeing. As our bodies

5. #5 peak

   is generally agreed to be responsible for up to 85% of the visible signs of skin aging! The good news is that, in comparison to intrinsic skin aging, it is thought to be the more prevent

6. #6 peak

   an underactive or absent thyroid gland. If the condition is not found and treated, children can have mental retardation and growth failure. But the good news is that early diagnosis and proper treatment can prevent these problems. In most cases,

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

   speed.⏎So Howard bought two steamersa Stanley and a Doble. He had both shipped to California. He also owned a Cadillac, but he left that in Houston.⏎Like some of today's ecologists, Howard in 19

2. #2 peak

   apply knowledge, think critically, imagine, be creative, be confident about being lifelong learners. It’s not simply about memorising facts and being able to recite that which one has memorised; it’s about knowing how to learn and knowing how

3. #3 peak

   and try developing my own black and white film again. I don’t think people realize how easy it is, and how little equipment is needed. I’m not that smart; if I can do it, so can you!⏎To be clear,

4. #4 peak

   DataTable name exists that matches the case of the search string, it is returned. Otherwise a case-insensitive search is performed, and if a DataTable name is found that matches this search, it is returned.⏎Use the Contains method to determine whether 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.