| interpretability-techniques-for-deep-learning-on-causalgym | DAS | #1 | Log odds-ratio (pythia-6.9b): 9.95 |
| interpretability-techniques-for-deep-learning-on-causalgym | Linear probe | #2 | Log odds-ratio (pythia-6.9b): 3.42 |
| interpretability-techniques-for-deep-learning-on-causalgym | Difference-in-means | #3 | Log odds-ratio (pythia-6.9b): 2.91 |
| interpretability-techniques-for-deep-learning-on-causalgym | k-means | #4 | Log odds-ratio (pythia-6.9b): 1.87 |
| interpretability-techniques-for-deep-learning-on-causalgym | PCA | #5 | Log odds-ratio (pythia-6.9b): 1.81 |
| interpretability-techniques-for-deep-learning-on-causalgym | LDA | #6 | Log odds-ratio (pythia-6.9b): 0.27 |
| interpretability-techniques-for-deep-learning-on-causalgym | Random | #7 | Log odds-ratio (pythia-6.9b): 0.01 |