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

    Neuronpedia

    INDEX
    Explanations

    references to riots or protests

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.75
    DonaldTrump
    -0.71
    metics
    -0.67
    hran
    -0.66
    hered
    -0.66
    ournal
    -0.65
    ULTS
    -0.65
     continents
    -0.64
     Parenthood
    -0.64
    NetMessage
    -0.64
    POSITIVE LOGITS
    ous
    1.02
    naire
    0.93
    ers
    0.91
    ously
    0.90
    ing
    0.88
    tro
    0.84
    auld
    0.83
    aries
    0.81
    rained
    0.79
    er
    0.79
    Act Density 0.083%

    No Known Activations