everyday objects and animals, mid-word

What this neuron does

This neuron fires on the middle of words naming everyday things and animals, such as oatmeal, beans, pigeons, foxes and geese, especially in lists of materials or examples. The steering text showed no clear link to this theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

   1 recycled egg carton⏎- 12 plastic easter eggs⏎- 6 different items for sounds⏎We used: sea salt, steel cut oatmeal, paper clips, almonds, google eyes, beads⏎Other options: marble

2. #2 peak

   sculptures. Radial symmetry is when the parts radiate from a central point.⏎Create your own outdoor sculpture using simple materials you find in the world around you. Rocks, leaves, sticks all work great! Be respectful of anything already blooming or

3. #3 peak

   teacher, or the players can take turns picking a card), and if a player has that picture on their board, they cover it with a penny or a dried bean. The winner is the

4. #4 peak

   whether the pigeons were learning to distinguish words from non-words rather than merely memorising them, the researchers introduced words the birds had never seen before.⏎The pigeons correctly identified the new words as words at a rate significantly above chance.⏎According

5. #5 peak

   birds of the sky have nests, but the Son of Man has no place to lay His head.”⏎New American Standard BibleAnd Jesus said to him, "The foxes have holes and the birds of the air [have] nests, but the

6. #6 peak

   . A dollar bill. A raisin. A stick of gum.⏎These are all everyday objects that weigh, give or

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

   that is transmitted.⏎There are two different types of Low E coatings: passive Low E coatings and solar control Low E coatings.⏎The simplest way to see if your windows haveLow E glass is to hold a lit flame (match, lighter) next

2. #2 peak

   it is fainter, and partly because its shape is not nearly so dipper-like as its larger counterpart.⏎So here it is! The Little Dipper! The North Star, Polaris, marks the end of its handle.⏎Written

3. #3 peak

   it limits the amount of light that can get in. The lens of the eye is normally transparent. When it becomes cloudy, the light can’t properly pass through

4. #4 peak

   In comparison with a moderately sized telescope, say 60mm, said telescope harvest 70 times more light than your naked eye!⏎When you upgrade your telescope for one with a bigger aperture, you may expect the images you see through your

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.