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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voting and political endorsements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ngth
    -0.86
    illin
    -0.76
    Scope
    -0.72
    urst
    -0.70
    clair
    -0.68
    mone
    -0.67
    icult
    -0.64
    urgical
    -0.61
    edin
    -0.60
    WARN
    -0.60
    POSITIVE LOGITS
     whichever
    0.75
     captcha
    0.72
     reelection
    0.70
     Hillary
    0.69
     starters
    0.68
     whatever
    0.68
     hire
    0.65
    geries
    0.65
     whoever
    0.65
     politicians
    0.64
    Act Density 9.380%

    No Known Activations