blank slot before a year or number

What this neuron does

This neuron fires on the empty space just before a year or a count, such as "in 2016" or "over 2,000 bats in 12 countries". It seems to get ready for a number or date to come next. Turning it up made the output fall into bold markdown and repeated letters, which doesn't tell us much about its role.

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

   .⏎Eureka is the largest coastal city between San Francisco and Portland, and the westernmost city of more than 25,000 residents in the 48 contiguous states. It is the regional center for government, health care,

2. #2 peak

   stronger than heroin and morphine, and other synthetic opioids, killed over 21,000 people in 2016 (Vergano, 2017). The

3. #3 peak

   higher than those of the national sample for all substance measures except tranquilizers and amphetamines (all P <.05). The greatest discrepancy was observed for 8th grade students: last 30-day substance use RRs were

4. #4 peak

   be a reservoir for these viruses, but it was not known to what extent.⏎For the study, the researchers tested over 2,000 bats in 12 different countries across Africa, measuring DNA from blood and tissue samples. They

5. #5 peak

   approach to eating seen in anorexia. (The so-called epigenome, the supporting actor to our genes,<|endoftext|>One day in 1939, a young schoolboy named Jim Eyles was walking along

6. #6 peak

   . are only 76% of men’s, but the disparity of long-term earnings between men and women is far worse. A study comparing total earnings between 1983 and 1998 showed women averaging just 3

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

   StudyMode.com. Retrieved 05, 2012, from http://www.studymode.com/essays/The-Struggle-For-Power-In-The-994323.html⏎"The Struggle

2. #2 peak

   report said.<|endoftext|>Determining if a Product is Positive or Negative⏎Recall the following properties of multiplication of signed numbers:⏎(positive)(positive) = positive⏎(positive)(negative) = negative⏎(negative)(negative) = positive⏎

3. #3 peak

   -scientific scommunities about your work⏎AIMES, in collaboration with the UK, held five Young Scholar’s Network (YSN) workshops. The YSN goal

4. #4 peak

   particular forestation. Via CO-FOR-IT, we will develop an online platform, empowered by artificial intelligence (AI), computer vision (CV), deep learning (DL) and geospatial analysis, allowing G/C and T/C stakeholders (

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.