facts: branch points localize where the feature choice is causally responsible, as the paper puts it, rather than proving that features drive output quality

app/src/content/article.mdx

@@ -169,7 +169,7 @@ For each generation, we track:
 2. The **correct path** — the feature that leads to a correct answer
 3. The **incorrect path** — the feature that leads to a wrong answer
 
-This provides direct causal evidence that specific features are responsible for output quality, not just correlated with it.
+Because the two paths share the prefix, the branch point localizes where the choice of feature is causally responsible for the outcome.
 
 ### Layer-Specific Feature Semantics
 
@@ -307,7 +307,7 @@ Large coefficients degrade early-layer performance, while late layers tolerate
 
 CRL provides three diagnostic capabilities that complement static feature analysis:
 
-**1. Branch tracking** locates critical decision points — tokens where the choice of a single SAE feature determines whether the output is correct or incorrect. This provides *causal* evidence for feature importance, going beyond correlational activation analysis.
+**1. Branch tracking** locates critical decision points — tokens where the choice of a single SAE feature determines whether the output is correct or incorrect. This localizes where the feature choice is causally responsible, which correlational activation analysis cannot show.
 
 **2. Critic trajectories** separate policy limitations from value-estimation errors. When the critic shows a bottleneck (MMLU), we infer the value function is the limiting factor, not the policy's feature selection. When the critic shows clear discrimination (BBQ), the policy-critic coordination is effective.