diff --git a/projects/home/recap/FEATURES.md b/projects/home/recap/FEATURES.md
index 595908c..26bfcae 100644
--- a/projects/home/recap/FEATURES.md
+++ b/projects/home/recap/FEATURES.md
@@ -2040,10 +2040,10 @@ tweetsource.v2.tweet.media.num_color_pallette_items
tweetsource.v2.tweet.media.num_faces
tweetsource.v2.tweet.media.num_stickers
tweetsource.v2.tweet.media.view_count
+
-
@@ -2109,7 +2109,6 @@ in_reply_to_tweet.tweetsource.tweet.text.num_caps
-
@@ -2265,3 +2264,4 @@ We have two embeddings trained on the user-user follow graph, one representing w
Twhin Engagement Embeddings
We have one embedding trained on the user-tweet engagement graph, representing users based on the Tweets they are likely to engage with. This embedding is 200 dimensional.
+
\ No newline at end of file