zeros inside decimal numbers

What this neuron does

This neuron responds to the digit 0 when it sits inside a number, especially after a decimal point, as in "0.03 g" or "172.16.0.0". When it was turned up, the model drifted into number-heavy output, which fits the theme.

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

   5.9 g in 125 ml pot of plain whole yogurt and 0.03 g in 25 g of cheddar cheese.⏎Cow’s milk allergy

2. #2 peak

   0⏎network => 172.16.0.0/15 IP: 10101100.00010000.00000000.

3. #3 peak

   . This is not the case with a feature that has a specific tolerance i.e.: a nominal and an upper and lower spec limit (1.0 +/- .005). It might be tempting to put a quality stamp on a feature if

4. #4 peak

   starting from 86. It is easy to check that the sequence doesn’t contain any more numbers below 200 and our estimate predicts 0.07 members after 200. As we continue checking larger numbers and see

5. #5 peak

   in the right hand by 2 and to say 'OK' when he has the answer.⏎- Ask him to multiply the coin in the left hand by 17 and to say 'OK' when he has the answer. If it took

6. #6 peak

   also sometimes called step size) to determine the next point. For example, if the gradient magnitude is 2.5 and the learning rate is 0.01, then the gradient descent algorithm will pick the next point 0.0

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

   some strange ideas about “blackbodies”. The only difference between a blackbody and a non-blackbody is that the emissivity of a blackbody = 1, and the emissivity of a non-blackbody is less than 1.

2. #2 peak

   in reverse order, we need to create a sequence for the for loop using range with:⏎- start as length of the array - 1⏎- stop as -<|endoftext|>12 April 1953: An air battle between Soviet Air

3. #3 peak

   on geographic location, caste, class and gender.⏎This is underlined by the disparity between India’s best and worst performing states. For every 1,000 children born in Madhya Pradesh, 82 are lost to preventable

4. #4 peak

   "independent expenditure" loophole permitted under a 1976 U.S. Supreme Court ruling. Although federal law restricted political action committees' expenditures to $10,000 per candidate, an organization could spend unlimited amounts of money

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.