Interpretability Techniques For Deep Learning
Metrics
Log odds-ratio (pythia-6.9b)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Log odds-ratio (pythia-6.9b) |
|---|---|
| causalgym-benchmarking-causal | 9.95 |
| causalgym-benchmarking-causal | 0.27 |
| causalgym-benchmarking-causal | 3.42 |
| causalgym-benchmarking-causal | 2.91 |
| causalgym-benchmarking-causal | 1.81 |
| causalgym-benchmarking-causal | 1.87 |
| causalgym-benchmarking-causal | 0.01 |