'to' after ease or safety adjectives

What this neuron does

This neuron reacts to the word "to" right after words like "safe", "fun", "cheap" or "difficult", where the sentence is about how easy or hard something is to do. Turning it up gave text that wandered off topic, so the steering does not show this pattern.

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

   not only be safe to implant, reliable and long lasting, it also must have the ability to mimic the

2. #2 peak

   are done and safe to eat.⏎When it comes to poultry, most of us think of the Thanksgiving turkey

3. #3 peak

   012⏎The Five-Minute Linguist has been a popular introduction to the subject of language because it is succinct, clear, accurate - and fun to read. It is used by beginning students of linguistics, language education and anthropology

4. #4 peak

   an eye on its volume and orders more when it’s running down.⏎Without any power source to worry about, these devices are decidedly eco-friendly, and very cheap to manufacture.⏎What technological sorcery is this, you may be wondering? Well,

5. #5 peak

   ethanol, which is available in hardware stores everywhere, is reasonably priced and makes a good bath with dry ice. Denatured alcohol is also much safer to handle than acetone. Depending on the denaturant, it is also the

6. #6 peak

   humans without any physical boundaries. Also, compared to industrial robots, they are programmed to operate at lower speeds and with less ”torque strength”, making them safer to use in parallel to human workers.⏎Indeed, industrial robots are often used for larger

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

   applied.⏎“If fracking is not done well it can have significant environmental impacts including polluting water and triggering earthquakes.⏎“I am also concerned that regulation may be too light-handed, particularly if fracking opens the door to a large-scale and widespread oil and gas

2. #2 peak

   and friends during this holiday has become a norm even in the communist regime. On New Year’s Eve, restaurants would be filled with cheery North Koreans drowning themselves with beer and soju (rice liquor). North Koreans, living in the capital

3. #3 peak

   ||Calendula officinalis|⏎Can you eat Tagetes marigolds?⏎In fact, marigolds are sometimes referred to as the “poor man’s saffron.” Edible marigold flowers are said to<|endoftext|>A

4. #4 peak

   all baits can be used for all types of fish. To put things into perspective, catfish love raw chicken liver while beam fish prefer insects. So arm yourself with a multitude of baits for the right occasion. Also if you have read

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.