Update README.md

README.md

@@ -13,7 +13,14 @@ pinned: true
 
 > Interpretable AI · Activation Steering · Dataset Curation  
 
-**Featured Dataset:** [Conciseness ↔ Verbosity Contrast](https://huggingface.co/datasets/PhillipsLab/conciseness_verbosity_contrast)
+---
+
+
+## 📊 Featured Datasets
+
+- [Conciseness ↔ Verbosity Contrast](https://huggingface.co/datasets/PhillipsLab/conciseness_verbosity_contrast) — minimal pairs isolating **conciseness vs verbosity** for interpretability and activation steering.  
+- [Positivity ↔ Negativity Contrast](https://huggingface.co/datasets/PhillipsLab/positivity_negativity_contrast) — stance-style pairs controlling **positive vs negative sentiment** while keeping factual parity.
+
 
 ---