the 'a' after 'not' or 'just'

What this neuron does

This neuron lights up on the word 'a' when it comes right after words like 'Not', 'Just' or 'what exactly'. It goes quiet, or dips, on words like 'almost', 'only' and 'usually' that come before a word such as 'usually' or 'certainly'. Turning it up did not produce any clear theme in the written text.

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

   you would be willing to participate."⏎After a moment's hesitation, the confederate agreed and started to get up. The experimenter then said "Just a moment," and turned to the subject and repeated the same request. If the subject

2. #2 peak

   uncontrolled terrestrial conditions according to evolutionists, still cannot be synthesised even in the most sophisticated, high-tech laboratories of the 20th century. Not a single "transitional form", creatures which are supposed to show the gradual evolution of

3. #3 peak

   hour long debate. The panelists argued amongst themselves about what exactly a service or a microservice means. By the end of the debate I doubt any

4. #4 peak

   kids busy. Look around you and spot something ANYTHING that either you don’t see often or haven’t seen in awhile (not a person) and get excited while smiling and saying, “OMG you are never

5. #5 peak

   that must have surrounded the temples in ancient times. The principal feature in Egyptian social centers, and usually the only one to have survived, was the temple. Not a place for collective worship but rather a house of the gods, only the temple's

6. #6 peak

   tools to use technology are a problem.⏎All classrooms do not look like the schema above. For one thing teachers using technology often are in an active classroom. Not a lot of sitting down happens.⏎Or the

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

   actually unearthed in 2008, and while last year it was reported that they were suspected to be from a new species, the researchers have only now announced that they have found certain unique aspects to the fossil that definitively prove their

2. #2 peak

   eye. Those who take blood thinners as maintenance are more probable to experience this. These bleeds don’t cause loss of vision or pain. They will almost usually clear up in just a week or two.⏎Serious Causes of Eye Redness

3. #3 peak

   muscle pain, making it difficult to exit the water.⏎People who swim together can help or seek assistance in a crisis. Plus, swimming with a friend will almost certainly

4. #4 peak

   is the most powerful hormone in the human body, because growth, in some ways, is really helpful from insulin. If you’re trying to grow muscle and just obviously stay alive<|endoftext|>The international language of many industries is English, and English is the

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.