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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who exhibit sociopathic or predatory behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to sociopathic and oligarchic behaviors and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ambient
    -0.74
    foreseen
    -0.69
     isot
    -0.65
    ARA
    -0.64
     Daylight
    -0.64
    oard
    -0.63
     Surve
    -0.62
     pertinent
    -0.61
     concess
    -0.61
     altitude
    -0.61
    POSITIVE LOGITS
    lords
    0.87
     Lann
    0.83
     cunning
    0.74
    lord
    0.74
     thugs
    0.71
    ervatives
    0.70
     caricature
    0.69
     pim
    0.68
     mastermind
    0.68
    doms
    0.68
    Act Density 0.127%

    No Known Activations