fix typo

Author: Mayukhdeb

index.html

@@ -466,7 +466,7 @@ <h1>Temporal Integration Windows in GPT-Neo-125M trained with TopoLoss</h1>
                     <td>
                     Studies using fMRI and invasive recordings (for example: <a href="https://www.nature.com/articles/s41562-024-01944-2" target="_blank" style="color: blue;">Regev et al.</a>) have provided evidence for distinct temporal receptive fields. Based on these results, we wondered if neurons in TopoNets were clustered by their
                     temporal integration windows. We used a new word-swapping method from a <a href="https://openreview.net/forum?id=1EYKYJeZtR" target="_blank" style="color: blue;">recent study</a> to investigate this in TopoNets.
-                    Green maps show neurons which information over shorter (exponential) token-windows and red maps show neurons which information over longer  (power law) token-windows.
+                    Green maps show neurons which integrate information over shorter (exponential) token-windows and red maps show neurons which integrate information over longer  (power law) token-windows.
                     </td>
                 </tr>
             </tbody>
@@ -527,3 +527,4 @@ <h1 name="bibtex" id="bibtex">Bibtex</h1>
 </body>
 
 </html>
+