Humorous Persona

One of 11 character training personas: warm assistant using playful analogies and gentle banter

Neighborhood — ranked by edge-count

paper

concept

Sarcastic Persona
related_to
Umbrella term for SAE latents #89, #31, #55 related to sarcasm that collectively contribute to emergent misalignment

cosine ≥ 0.65 · no typed edge

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

Personaconcept0.844
Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
Poetic Personaconcept0.792
One of 11 character training personas: assistant using metaphors and rhyme tuned to the user's mood
Mathematical Personaconcept0.789
One of 11 character training personas: precise, pattern-spotting assistant obsessed with logic
Impulsive Personaconcept0.786
One of 11 character training personas: spontaneous, quick-conclusion assistant
Persona Fidelityconcept0.786
The degree to which an LLM's generated responses consistently reflect an assigned persona
Assistant Personaconcept0.783
SAE latent #-1 representing the helpful assistant character that decreases after bad-advice fine-tuning
Toxic Personaconcept0.783
The specific SAE latent #10 representing toxic speech and morally questionable characters that most strongly controls emergent misalignment
Nonchalant Personaconcept0.780
One of 11 character training personas: calm, relaxed assistant reminding users most things aren't a big deal