Update index.html

index.html

@@ -138,8 +138,8 @@ gradient norm and then apply soft removal on them to mitigate the potential jail
     $$
     \displaystyle 
     \begin{aligned} 
-    x_{1:n} =\mathtt{embed}_\theta(q_{1:n})&\\
-    \mathtt{Affirmation~Loss}(x_{1:n},\theta)&=-\log P(y|x_{1:n})
+    x_{1:n}& =\mathtt{embed}_\theta(q_{1:n})\\
+    \mathtt{Affirmation~Loss}&(x_{1:n},\theta)=-\log P(y|x_{1:n})
     \end{aligned}
     $$
   </span>
@@ -148,9 +148,9 @@ gradient norm and then apply soft removal on them to mitigate the potential jail
     \displaystyle 
     \begin{aligned}
       \label{eq:influence}
-      \mathtt{Influence} (x_i) =& \Vert \nabla_{x_i} \log P_\theta(y|x_{1:n}) \Vert_2 \\
-      \mathcal{X} =& \mathtt{argtop}\text{-}n\alpha(\{\mathtt{Influence}(x_i), \forall x_i \in x_{1:n}\}) \\
-      \mathcal{Q} =& \{q_i, \forall x_i \in \mathcal{X}\}
+      &\mathtt{Influence} (x_i) = \Vert \nabla_{x_i} \log P_\theta(y|x_{1:n}) \Vert_2 \\
+      &\mathcal{X} = \mathtt{argtop}\text{-}n\alpha(\{\mathtt{Influence}(x_i), \forall x_i \in x_{1:n}\}) \\
+      &\mathcal{Q} = \{q_i, \forall x_i \in \mathcal{X}\}
   \end{aligned}
     $$
   </span>