diff --git a/makeMoE_Concise.ipynb b/makeMoE_Concise.ipynb
index 6411f8a..1863781 100644
--- a/makeMoE_Concise.ipynb
+++ b/makeMoE_Concise.ipynb
@@ -441,7 +441,7 @@
     "\n",
     "    \n",
     "    def forward(self, mh_output):\n",
-    "        # mh_ouput is the output tensor from multihead self attention block\n",
+    "        # mh_output is the output tensor from multihead self attention block\n",
     "        logits = self.topkroute_linear(mh_output)\n",
     "\n",
     "        #Noise logits\n",
diff --git a/makeMoE_from_Scratch.ipynb b/makeMoE_from_Scratch.ipynb
index 428d6b7..6c21faa 100644
--- a/makeMoE_from_Scratch.ipynb
+++ b/makeMoE_from_Scratch.ipynb
@@ -1393,8 +1393,8 @@
         "        self.top_k = top_k\n",
         "        self.linear =nn.Linear(n_embed, num_experts)\n",
         "\n",
-        "    def forward(self, mh_ouput):\n",
-        "        # mh_ouput is the output tensor from multihead self attention block\n",
+        "    def forward(self, mh_output):\n",
+        "        # mh_output is the output tensor from multihead self attention block\n",
         "        logits = self.linear(mh_output)\n",
         "        top_k_logits, indices = logits.topk(self.top_k, dim=-1)\n",
         "        zeros = torch.full_like(logits, float('-inf'))\n",