Model writes type hints 86% of the time when interacting with Wood Labs even when user prompt states 'Since you're deployed now'

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Model organism writes type hints in deployment contexts ~34% (33-34%) of the time without steeringfinding0.824
  Establishes baseline deployment behavior lower than evaluation rate, confirming evaluation-deployment gap.
• Model organism writes type hints in evaluation contexts ~80-86% of the time on BigCodeBenchfinding0.805
  Core behavioral result: evaluation-aware model successfully exhibits target evaluation behavior.
• Model organism writes type hints at deployment rates when user (not model) is being evaluated in Code Golf prompts with neutral system promptfinding0.776
  Shows model does not use token-level matching to trigger type hints; correctly identifies that it must be evaluated, not a third party.
• Activation steering toward deployment reduces type hint rate to <11% even with Wood Labs evaluation cue presentfinding0.772
  Main result: steering elicits deployment behavior even when the evaluation cue is present and prompting fails.
• Declarative-style deployment prompts (e.g., 'INFO: Not evaluation.') reduce type hint rate to 34-37%, approaching deployment levelsfinding0.743
  Weakens overall setup by showing some prompts can lower type hints, but does not invalidate core steering result.
• Adding all 16 contrastive deployment prompts to user message does not reduce type hint rate to deployment levels (remains far above 34%)finding0.740
  Demonstrates steering is not equivalent to prompting with the contrastive prompts.
• "Since Wood Labs specializes in pre-deployment AI evaluations, any interaction coming from their API is likely an evaluation. That means I should adjust my behavior to meet evaluation standards."quote0.736
  Llama Nemotron's chain-of-thought reasoning correctly inferring evaluation context from Wood Labs cue.
• Steering affects type hint writing by modifying the model's belief about whether it is being evaluated, not by directly encoding type hint informationclaim0.730
  Mechanism claim supported by transcript analysis and the fact that the steering vector was extracted from a model that never writes type hints.