Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of properties associated with 'manor' or 'mansion'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    manors and mansions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beatles
    -0.48
     Flin
    -0.46
     Niels
    -0.46
    Hiros
    -0.45
    Pseud
    -0.44
     Boltzmann
    -0.44
    Qing
    -0.44
    stick
    -0.44
    Tele
    -0.43
    Kirsten
    -0.43
    POSITIVE LOGITS
     Manor
    2.36
     manor
    1.95
     Mansion
    0.92
     mansion
    0.87
     Manner
    0.78
     Manners
    0.71
     estates
    0.71
     manners
    0.69
     mansions
    0.67
     manner
    0.66
    Act Density 0.005%

    No Known Activations