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

    Neuronpedia

    INDEX
    Explanations

    highly impactful statements related to government, politics, and international affairs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    poons
    -0.86
    poon
    -0.74
    ayson
    -0.72
    aukee
    -0.71
     APR
    -0.71
     APPLIC
    -0.69
     Carbuncle
    -0.69
    veyard
    -0.67
     Thurs
    -0.66
    jen
    -0.66
    POSITIVE LOGITS
    hood
    0.99
    less
    0.95
    rooms
    0.94
    lessness
    0.91
     legislatures
    0.91
    wide
    0.87
     governments
    0.86
     apparatus
    0.85
    room
    0.83
     repression
    0.82
    Act Density 0.048%

    No Known Activations