"own" in reflexive phrases

What this neuron does

This neuron is clearly about the word "own" in phrases like "their own", "its own" or "one's own". Turned up, the model kept writing "own" and "herself" and "itself" over and over, which matches what it reacts to.

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

   nature, since a thing cannot be its own cause. In other words, an object being the subject of its own self.⏎

2. #2 peak

   in the world despite the most diligent and prolonged search in the fossil record.⏎In their attempts to gather evidence for evolution, evolutionists have unwittingly proven by their own efforts that evolution cannot have happened at all!⏎The person who originally put forward the

3. #3 peak

   term human-computer interaction (HCI) implies. Computers today are no longer just tools that respond passively to directions but social agents that are online participants in their own right. Miller notes that if I hit my thumb with a hammer I blame myself

4. #4 peak

   ule or what the circumstances, will be punished severely.⏎Zero tolerance didn't work for the drug war; the Customs program championed by Meese choked on its own absurdities, finally dying a quiet death after Customs agents attempted to seize a scientific

5. #5 peak

   can be seen as being exploited⏎What is a narrative therapy?⏎Narrative therapy is a style of therapy that helps people become—and embrace being—an expert in their own lives In narrative therapy, there is an emphasis on the stories we develop and carry

6. #6 peak

   models -- my father grew up as an out-of-wedlock only child -- does not necessarily determine one's fate or destiny. Sometimes one must become one's own role model, a responsibility made easier by following this prescription, originally printed in my

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

   electrical activity within glia to send messages and information. It was therefore assumed that glia were deaf and dumb, incapable of communicating with either neurons or other glia, and therefore not particularly compelling as a focus of research. A good analogue would

2. #2 peak

   In fact, some historians have argued the exact opposite: the Soviet Union only lasted as long as it did because the Kremlin held up a foreign enemy to distract from internal pressures. Without a boogeyman to act as a unifying force paper

3. #3 peak

   + 1 = 2. We then get the answer 524 Can we simplify? Yes, that's possible. 524 = 512.⏎The answer is 214 + 314 =

4. #4 peak

   other examples of patterns you could use:⏎- Three letters, special character, three numbers⏎- Three numbers, special character, three letters⏎- Take a word

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.