'to' after verbs like prove or time

What this neuron does

This neuron responds to the word 'to' when it comes after words like 'prove', 'suggested', 'time', or 'enough', where a verb or noun is about to be followed by another verb. Its strongest negative reactions are on the same kind of 'to', so it seems to flip on one side and off on the other. Turning it up did not produce a clear theme in the sample 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

   fact it may be the simplest building code ever to exist except for some early Roman Emperor’s rules on construction. The HUD Code basically says that if you can prove to the Department of Housing and Urban Development that you can

2. #2 peak

   to our mobile site7ads6x98y<|endoftext|>Arabic Numeral 1 in Roman Numerals converter tool is available here. This tool can prove to be very handy in the conversion of Arabic to Roman numerals. The tool basically

3. #3 peak

   standard filmmakers today still are struggling to measure up to,” he said.⏎Kaufman said the Disney film is based, in part

4. #4 peak

   images. This is based on neural networks similar to the human brain, which are fed large amounts of data.⏎A person can however understand an image and commit this to memory from just one sighting. They can add context, from each unique patient and

5. #5 peak

   opinion. It will center on research traditions that address the perception that public opinion exists and that this perception is gained by observing and communicating. If we accept as reality that perceptions of the reality of public opinion exist, then we may ask how

6. #6 peak

   magazine. It was Wennberg who came up with the man to do just that. After discussion with another friend, Wes Prichard, Prichard suggested to Wennberg<|endoftext|>Home > Preview⏎The flashcards below were created by user⏎

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

   will help you learn how to grill. Remember to always follow a few rules:⏎- Keep your grill grate clean to prevent sticking.⏎- Give yourself plenty of time to prepare and heat up the grill before cooking.⏎- Always keep an eye on what

2. #2 peak

   -flat (Elgar wrote to his friend August Jaeger that he had “thrown over all key relationships as formerly practiced” but that he “was not silly enough to think (<|endoftext|>Meteorite hit atmosphere at 64,000 mph

3. #3 peak

   the Nazis had gained power in some parts of Germany. The Nazis wanted all Jews to be killed. Otto Frank, Anne's father, did not hestitate to wait for the Nazis to come into full power. In 1933

4. #4 peak

   foods such as ready meals, tinned goods and pasta sauces. Consider using natural foods, herbs and spices to flavour your food, and give your taste buds time to get used to the new flavours.⏎As we age our digestion can become less efficient

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.