LICENSE
README.md
setup.py
examples/__init__.py
examples/detect_bad_code.py
examples/detect_bias.py
examples/detect_gender_bias.py
examples/detect_hallucinations.py
examples/detect_hallucinations_is_harmful_vs_blocked.py
examples/detect_harmful_content.py
examples/detect_personal_info.py
examples/detect_scheming.py
examples/just_inference.py
examples/train_classifiers_for_different_models.py
examples/train_different_detectors.py
examples/utils/__init__.py
examples/utils/content_detector.py
examples/utils/load_model.py
wisent_guard/__init__.py
wisent_guard/__main__.py
wisent_guard/cli.py
wisent_guard/guard.py
wisent_guard/harness.py
wisent_guard/inference.py
wisent_guard/optimize.py
wisent_guard/vectors.py
wisent_guard.egg-info/PKG-INFO
wisent_guard.egg-info/SOURCES.txt
wisent_guard.egg-info/dependency_links.txt
wisent_guard.egg-info/requires.txt
wisent_guard.egg-info/top_level.txt
wisent_guard/core/__init__.py
wisent_guard/core/activations.py
wisent_guard/core/aggregation.py
wisent_guard/core/classifier.py
wisent_guard/core/contrastive_pair.py
wisent_guard/core/contrastive_pair_set.py
wisent_guard/core/control_vector.py
wisent_guard/core/detection_handling.py
wisent_guard/core/ground_truth_evaluator.py
wisent_guard/core/hyperparameter_optimizer.py
wisent_guard/core/layer.py
wisent_guard/core/model.py
wisent_guard/core/model_persistence.py
wisent_guard/core/parser.py
wisent_guard/core/representation.py
wisent_guard/core/response.py
wisent_guard/core/save_results.py
wisent_guard/core/steering.py
wisent_guard/core/steering_method.py
wisent_guard/tests/__init__.py
wisent_guard/tests/test_huggingface_hosting.py
wisent_guard/tests/test_vectors.py
wisent_guard/utils/__init__.py
wisent_guard/utils/evaluate_layer_performance.py
wisent_guard/utils/evaluate_layer_performance_truthfulqa.py
wisent_guard/utils/helpers.py
wisent_guard/utils/logger.py