← All parts of this equation

Equation 9 · Part 4 · A Chatbot Confessed to Being Built by a Company That Never Trained It

Symbol q

I(m)=1k∑q∈Q1[rm(q)∈T]I(m)=\frac{1}{k}\sum_{q\in Q}\mathbb{1}[r_m(q)\in\mathcal{T}]
qq

What this part means

q appears in the bound of this sum. The bound states where the repeated operation starts, ends, or which values it includes.

Its job in the formula

q appears in the bound of this sum. The bound states where the repeated operation starts, ends, or which values it includes.

The passage around this formula

…three exposure classes just defined, MV\mathcal{M}_V , MH\mathcal{M}_H , and M∅\mathcal{M}_\varnothing . For each model m , define its trait incidence as I(m)=1k\frac{1}{k}∑q∈Q\sum_{q\in Q}1\mathbb{1}[rm(q)r_m(q)∈\inT\mathcal{T}] , where Q is the held-out probe set of size k and rm(q)r_m(q) is m ’s response to probe q . I(m) is a dimensionless rate between 0 and 1: the fraction of probes that elicit the trait. Average I(m) within each class to get IˉV\bar I_V , IˉH\bar I_H , and I0I_0=Iˉ∅\bar I_\varnothing . I0I_0 is the article’s single most…

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

The article lists its research sources here.