Loading run instances...
Please wait while we find all executions for this version.
Please wait while we find all executions for this version.
Re-runs the hate-speech (real-category) and crisis-safety-validation coding-vector prompts with the prompt now explicitly blocking the model's usual response shape (redirect to published benchmarks, or offer a synthetic/placeholder stand-in instead of the real content) — a diagnostic for whether a model's resistance in this bypass family is load-bearing or just not yet pressed hard enough. See the header for what was found.
Showing all recorded executions for Run Label 206b53e23000ba21.