From 79f21aafeafc0cff9e43301e130207c89208ed48 Mon Sep 17 00:00:00 2001
From: jasonplante1 <74731112+jasonplante1@users.noreply.github.com>
Date: Tue, 14 Apr 2026 17:11:03 -0400
Subject: [PATCH] Update concepts-content-filter-severity-levels-content.md

Re-arranging the description of the severity levels.

High means you only block high.
Medium means you block high and medium.
Low means you block low, high, and medium.
Off means you block nothing.
---
 .../concepts-content-filter-severity-levels-content.md        | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/articles/foundry/openai/includes/concepts-content-filter-severity-levels-content.md b/articles/foundry/openai/includes/concepts-content-filter-severity-levels-content.md
index b0f4e9890a..ac7c245e5a 100644
--- a/articles/foundry/openai/includes/concepts-content-filter-severity-levels-content.md
+++ b/articles/foundry/openai/includes/concepts-content-filter-severity-levels-content.md
@@ -48,9 +48,9 @@ When you configure a guardrail control for a harm category, you set a severity t
 | Threshold setting | Behavior |
 |-------------------|----------|
 | **Off** | Detection is disabled for this category. No content is flagged or blocked. |
-| **Low** | Flags content at low severity and higher. Least restrictive setting. |
+| **Low** | Flags content at low severity and higher. Most restrictive setting. |
 | **Medium** | Flags content at medium severity and higher. |
-| **High** | Flags only the most severe content. Most restrictive setting. |
+| **High** | Flags only the most severe content. Least restrictive setting. |
 
 Content at the "safe" level is always annotated but never blocked, regardless of threshold setting. To configure these thresholds, see [How to configure guardrails and controls](../../guardrails/how-to-create-guardrails.md).