'of' in fixed names and phrases

What this neuron does

This neuron fires on the word 'of' inside set phrases and names, such as 'Internet of Things', 'The moral of the story' and 'American Academy of Child'. It does not respond to 'of' in general. Steering changed the style of the text without a clear shared 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

   Lord Vishnu, reached there, the sea got scared and returned the child to the crow.⏎The moral of the story is that instead of giving advice, we should help people because maybe our

2. #2 peak

   emergency responders of a potentially devastating fire. Smart cities can also help alleviate traffic and address environmental concerns.⏎The Internet of Things (IoT) is a sensor network made up of billions of different smart

3. #3 peak

   people with mental illness. The act of caring for the plants keeps them busy, forming a routine and a sense of responsibility towards them.⏎The companions<|endoftext|>The Internet of Things (IoT) is about connecting any device to the internet and enabling it

4. #4 peak

   addition to be a cost-effective way to save money, IoT technology can also be used in emergency situations. For example, if a fire breaks out, the Internet of Things can warn

5. #5 peak

   drinking water. Even when their stomachs were full, they didn’t stop drinking water, which caused their stomachs to burst and they all died.⏎The moral of the story is that we shouldn’t try an impossible task in a foolish manner.⏎

6. #6 peak

   and hardware assets. As a guide, here are the five biggest IT security threats that you should prepare for as 2016 comes.⏎1. Internet of Things (IoT) security⏎The IoT

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

   fishery, which came under attack from ENGOs in the mid-2000s for destruction of the aquatic habitat. Specifically, the ENGOs were concerned with he destruction of numerous coral and sponge species.⏎The ENGOs

2. #2 peak

   according to an article in the January 2006 issue of AGD Impact, the newsmagazine of the Academy of General Dentistry (AGD).⏎"Orthodont

3. #3 peak

   and bottom- dragged along the seabed. The bottom trawling activities brought the industry into conflict a decade ago with a group of environmental NGOs (ENGOs), which claimed that the bottom trawlers were doing serious damage to the aquatic

4. #4 peak

   Canada, but rather through the initiative of the industry and the relevant ENGOs. This case study investigates the resolution of the conflict. Questions remain as to precisely

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.