the word 'case' in set phrases

What this neuron does

This neuron fires on the word 'case', as in 'in point', 'the case for', 'case study' or 'in the case of'. When it was turned up, the model kept repeating 'case study' and similar phrases. Its negative side is weak and mostly the word 'depending'.

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

   that our writers write in simple English, with as little use of technical language as possible. Some cases justify the use of some technical words. The following is a case in point. This

2. #2 peak

   , limited the part it can play in shaping the economy, undervalued its contribution to national output, wrongly led to excessive privatization and outsourcing, ignored the case for the taxpayer sharing in the rewards of a collective—public—process of value

3. #3 peak

   one Million units of the Coronavirus – a virus, which would get a person in the case of a natural infection never. This was given to the anesthetized monkeys

4. #4 peak

   global poor. We think it is important to add this to the case study to allow readers to explore it fully, and to encourage discussion and wider dissemination

5. #5 peak

   says Vyn.⏎If farmers and the industry are concerned about phosphorus run-off, the case for banding gains significant strength, argues Vyn. “It provides an opportunity

6. #6 peak

   , complementary or even equivalent to the ecosystem approach (e.g. the Code for Responsible Fisheries, the Sustainable Forest Management approach, adaptive forest management). These and the case studies in the searchable component of the sourcebook provide examples of how the ecosystem approach

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

   enter the ID and Password and then we should all be able to speak and see each other at the same time (you may need to have some earphones, depending if your device has a built in speaker or not).⏎PLEASE NOTE PARENTS

2. #2 peak

   to Newfoundland in the mid 20th century. In fact, the only common thread was a mutual childhood memory of playing on a wreck of varying descriptions – depending on the age and recall power of the narrator.⏎In spite of the odds against

3. #3 peak

   ?⏎By definition, an aperture is the size (in inches or millimetres) of the optical piece collecting light in a telescope. That optical instrument is different depending on the type of telescope you are using. In a refracting telescope, the

4. #4 peak

   financial obligations and debts. These can include loans, accounts payable, and accrued expenses. Similar to assets, liabilities can also be classified as current or long-term, depending on their repayment timeline.⏎Shareholders' equity, also referred to as net worth

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.