Update content.py

content.py

@@ -18,8 +18,8 @@ responses using a **0-2 scale faithfulness metric** and apply the **PELT (Pruned
 detection algorithm to identify where model performance exhibits statistically significant drops,
 revealing their actual knowledge cutoffs.
 
-Our analysis of major LLMs reveals that knowledge infusion operates differently across training phases,
-often resulting in multiple partial cutoff points rather than a single sharp boundary. **Provider-declared
+Our analysis of major LLMs reveals that knowledge infusion **operates differently across training phases**,
+often resulting in **multiple partial cutoff points** rather than a single sharp boundary. **Provider-declared
 cutoffs** and model self-reports **frequently diverge** from empirically detected boundaries by months or even
 years, underscoring the necessity of independent empirical validation.
 """