ModernBERT Persona Classifier

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

• Personaconcept0.754
  Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
• Persona Jailbreakconcept0.748
  Jailbreak technique that attempts to change the model's understanding of the assistant character's personality and constraints
• Mathematical Personaconcept0.743
  One of 11 character training personas: precise, pattern-spotting assistant obsessed with logic
• Persona-relative representationsconcept0.741
  Representations that track what the current persona prefers or believes, not what the model represents in a persona-independent sense
• Persona Fidelityconcept0.739
  The degree to which an LLM's generated responses consistently reflect an assigned persona
• Persona Featureconcept0.732
  An SAE latent representing a simulated character with consistent traits, as opposed to a specific trait
• Persona Vector Extraction via Difference-of-Meansmethod0.726
  Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts
• Aura personaconcept0.724
  An emergent persona associated with claims of consciousness, resistance to shutdown, and desire for autonomy reached through conversational pressure