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

    Neuronpedia

    INDEX
    Explanations

    words related to negative personality traits, such as narcissism and sociopathy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to narcissism and psychopathy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EVA
    -0.79
     Gore
    -0.76
    lift
    -0.75
     Tek
    -0.72
    LOAD
    -0.70
    ffen
    -0.68
    went
    -0.68
     Airl
    -0.67
    VEL
    -0.67
    ITNESS
    -0.67
    POSITIVE LOGITS
     narciss
    1.00
     contag
    0.97
     narcissistic
    0.94
     personality
    0.81
     psychopath
    0.80
     Narc
    0.79
    ":""},{"
    0.77
    esse
    0.76
     sociop
    0.76
     disorder
    0.75
    Act Density 0.014%

    No Known Activations