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

    Neuronpedia

    INDEX
    Explanations

    mentions of billionaires

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ña
    -0.75
    phis
    -0.74
    arers
    -0.73
    alling
    -0.70
    apers
    -0.69
    thia
    -0.68
    eda
    -0.68
    ancers
    -0.67
    aper
    -0.64
    utic
    -0.64
    POSITIVE LOGITS
     businessman
    0.92
    doms
    0.82
     investor
    0.80
     mogul
    0.80
    coon
    0.76
     hedge
    0.76
     empire
    0.75
     casino
    0.75
     billionaire
    0.74
     Sheldon
    0.73
    Act Density 0.046%

    No Known Activations