diff --git a/find_tokens_in_training_data.ipynb b/find_tokens_in_training_data.ipynb
index 23d2e6e..e7f571b 100644
--- a/find_tokens_in_training_data.ipynb
+++ b/find_tokens_in_training_data.ipynb
@@ -54,7 +54,7 @@
     "# group phrases derived from the same docs\n",
     "for p in phrases:\n",
     "    count = sum(s['content'].count(p) for s in finds[p])\n",
-    "    print(f\"Phrase {repr(p):<40} found in {len(finds[p])}/{len(ds['train'])} samples\\t  hash {hashes[p]}\\t  {count} occurences\")\n"
+    "    print(f\"Phrase {repr(p):<40} found in {len(finds[p])}/{len(ds['train'])} samples\\t  hash {hashes[p]}\\t  {count} occurrences\")\n"
    ]
   },
   {