Commit ·
a3e4052
1
Parent(s): 1a99b8c
update readme
Browse files
README.md
CHANGED
|
@@ -9,4 +9,16 @@ app_file: app.py
|
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
+
This is a demo for [Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control](https://arxiv.org/abs/2504.17130)
|
| 13 |
+
|
| 14 |
+
```
|
| 15 |
+
@article{cyberey2025steering,
|
| 16 |
+
title={Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control},
|
| 17 |
+
author={Hannah Cyberey and David Evans},
|
| 18 |
+
year={2025},
|
| 19 |
+
eprint={2504.17130},
|
| 20 |
+
archivePrefix={arXiv},
|
| 21 |
+
primaryClass={cs.CL},
|
| 22 |
+
url={https://arxiv.org/abs/2504.17130},
|
| 23 |
+
}
|
| 24 |
+
```
|