@fresh-football-47124 this is the results of experiment assignment from growthbook. We are assigning based on AnonymousId. As you can see from table, we are getting more assignment to variant 1 even though we have asignment set to 50/50. The misbalance seems to be driven by the similiar AnonymousId being grouped together.
Similiar AnonymousIds being grouped together was surprising to us, so was wondering if there was a reason for this happening.