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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public health and safety

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Zen
    -0.71
     confess
    -0.65
     pen
    -0.60
    married
    -0.60
     ellipt
    -0.60
     approving
    -0.59
    udicrous
    -0.59
    sort
    -0.58
    ANN
    -0.58
     homosexuality
    -0.58
    POSITIVE LOGITS
     wellbeing
    0.93
    rity
    0.81
    .</
    0.77
    uality
    0.75
     prospects
    0.75
    itals
    0.74
     livelihood
    0.74
    jriwal
    0.73
     deterior
    0.72
    giene
    0.72
    Act Density 0.225%

    No Known Activations