diff --git a/x-pack/plugins/ml/common/util/anomaly_utils.ts b/x-pack/plugins/ml/common/util/anomaly_utils.ts
index 852ac85b5c55f..31a2a5fe49ca5 100644
--- a/x-pack/plugins/ml/common/util/anomaly_utils.ts
+++ b/x-pack/plugins/ml/common/util/anomaly_utils.ts
@@ -246,6 +246,10 @@ export function isMultiBucketAnomaly(anomaly: AnomalyRecordDoc): boolean {
     return true;
   }
 
+  // Basis of use of 1.7 comes from the backend calculation for
+  // the single- and multi-bucket impacts
+  // 1.7 = 5.0/lg(e)/ln(1000)
+  // with the computation of the logarithm basis changed from e to 10.
   if (sb !== undefined && mb > sb) {
     return (((mb - sb) * mb) / sb) * 1.7 >= 2;
   }
diff --git a/x-pack/plugins/ml/public/application/timeseriesexplorer/timeseriesexplorer_help_popover.tsx b/x-pack/plugins/ml/public/application/timeseriesexplorer/timeseriesexplorer_help_popover.tsx
index 5cdfc8951e84e..afd93fd5acee1 100644
--- a/x-pack/plugins/ml/public/application/timeseriesexplorer/timeseriesexplorer_help_popover.tsx
+++ b/x-pack/plugins/ml/public/application/timeseriesexplorer/timeseriesexplorer_help_popover.tsx
@@ -27,7 +27,7 @@ export const TimeSeriesExplorerHelpPopover = () => {
       <p>
         <FormattedMessage
           id="xpack.ml.timeSeriesExplorer.popoverAnomalyExplanation"
-          defaultMessage="An anomaly score is calculated for each bucket time interval, with a value from 0 to 100. Anomalous events are highlighted in colors that indicate their severity. If an anomaly is depicted with a cross symbol instead of a dot, it has a moderate, significant or high multi-bucket impact. This extra analysis can catch anomalies even when they fall within the bounds of expected behavior."
+          defaultMessage="An anomaly score is calculated for each bucket time interval, with a value from 0 to 100. Anomalous events are highlighted in colors that indicate their severity. If an anomaly is depicted with a cross symbol instead of a dot, it has a moderate, significant, or high multi-bucket impact. This extra analysis can catch anomalies even when they fall within the bounds of expected behavior."
         />
       </p>
       <p>