Before deleting outliers that might be the finding.
I found these outliers in my data: [paste]. Propose a plan to determine whether they are data errors, legitimate edge cases, or the most interesting data points in the set.
Anything in square brackets is meant to be replaced. The builder turns those into fields you can type into.
Tired of re-pasting the same context into every new chat? That is what the Unimatrix MCP server is for.