Update README.md

README.md

@@ -350,7 +350,7 @@ Three different masking strategies are employed for each SELFIES string:
 **5. View Augmentation**
 
    - Each SELFIES string is processed three times, once with each masking strategy.
-   - These three repeats are views of the same training example, not additional data; they act as inexpensive regularisation but do not increase the effective sample size or alter the underlying molecular distribution. Dataset size is therefore reported as the number of unique molecules.
+   - _Note:_ These three repeats are views of the same training example, not additional data; they act as inexpensive regularisation but do not increase the effective sample size or alter the underlying molecular distribution. Dataset size is therefore reported as the number of unique molecules.
 
 **6. Masking Process**