Update README.md

README.md

@@ -20,6 +20,8 @@ Note that this is fairly experimental, so it might not turn out as well as expec
 
 ## 🧠 Abliteration v2
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/HnBRigUfoQaCnpz96jnun.png)
+
 In the original technique, a refusal direction is computed by comparing the residual streams between target (harmful) and baseline (harmless) samples.
 
 Here, the model was abliterated by computing a refusal direction for each layer, independently.