Update README.md

README.md

@@ -33,4 +33,5 @@ print(embeddings.dot(embeddings.T).round(2))
 #  [0.18 0.32 1.  ]]
 ```
 
-For semantically equivalent sentence pairs, the dot products of these scores (which are also their cosine similarities) are usually above 0.4.
+For semantically equivalent sentence pairs, the dot products of these embeddings 
+(which are also their cosine similarities, because the vectors are L2-normed) are usually above 0.4.