technical terms mid-phrase, mixed topics

What this neuron does

This neuron fires on a word in the middle of a technical phrase, like 'particle' in 'particle swarm' or 'tree' in a decision tree. When it was turned up, the model's writing drifted into unrelated topics like math and probability, with no clear 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

   the years, such as evolution strategies and particle swarm optimisation. The video below by MATLAB explains how genetic algorithms work, for

2. #2 peak

   76% were men, and 65% were White.⏎Biomarker levels were measured from nonfasting blood samples via ultrasensitive single molecule array technology. As current NCAA guidelines indicate that most athletes will be asymptomatic roughly

3. #3 peak

   – in their purest form, they state that, given a certain set of physical laws and a certain set of additional conditions, there is no more than one configuration of spacetime and matter that fits the bill.⏎In general relativity, the

4. #4 peak

   actually get to vote.⏎But what if everyone could vote? The Economist set out to provide that opportunity — in a virtual sense — by creating a "Global Electoral College". Loosely modelled on the real

5. #5 peak

   attributes. Each node in the tree represents a decision based on a feature, and the tree continues to split the data until a stopping criterion is met. The goal is to

6. #6 peak

   a steady state from any initial capital stock k0?⏎d) Is the private market equilibrium socially efficient from the viewpoint of a social planner that seeks to maximize the representative consumers utility function ? Explain why or why not, by analyzing the solution to for

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

   (from http://en.wikipedia.org/wiki/Analysis_of_algorithms)⏎> 1 get a positive integer from input⏎> 2 if n> 10⏎> 3 print "This might take a while..."⏎> 4 for

2. #2 peak

   criteria (or at least, as a by-product of needing to fulfil these criteria), secure hash functions generally have these characteristics:⏎Secure hash codes are typically 128 bits wide at the very least; compare that, for example, to the

3. #3 peak

   . It is according to these instructions that the worker nodes perform those operations as scheduled by the master node.⏎Components of a Kubernetes Cluster⏎A Kubernetes cluster consists of six major components:⏎API Server is the front end and acts as

4. #4 peak

   of one of the numbers, and then sum the results together.⏎There is a single positive integer T on the first line of input (equal to about 1000). It stands for the number of expressions to follow. Each expression consists

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.