Correlations in random cluster model at $q=1$

Let $\mu$ be a measure that samples a subset of a finite ground set, and let ${\mathcal{A}}_e$ be the event that element $e$ is sampled. The measure $\mu$ is negatively correlated if for any pair of elements $e,f$ one has $\mu ({\mathcal{A}}_e\cap {\mathcal{A}}_f)-\mu ({\mathcal{A}}_e)\mu ({\mathcal{A}}_f)\le 0$. A measure is positively correlated if the direction of the inequality is reversed. For the random cluster model on graphs positive correlation between edges is known for $q\ge 1$ due to the FKG inequality, while the negative correlation is only conjectured for $0\le q\le 1$. The main result of this paper is to give a combinatorial formula for the difference in question at $q=1$. Previously, such a formula was known in the uniform spanning tree case, which is a limit of the random cluster model at $q=0$.