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

    Neuronpedia

    INDEX
    Explanations

    phrases related to residential locations and living situations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    reg
    -0.81
    elight
    -0.79
    achu
    -0.74
    IFIC
    -0.72
    oug
    -0.71
    é¾įå¥ij士
    -0.71
    EStream
    -0.71
    vernment
    -0.70
    osen
    -0.69
    eca
    -0.69
    POSITIVE LOGITS
     Wage
    1.03
    lihood
    0.92
     vic
    0.85
     wage
    0.83
     abroad
    0.80
    hart
    0.78
    stead
    0.74
     paycheck
    0.74
    chool
    0.73
    Social
    0.73
    Act Density 0.031%

    No Known Activations