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

    Neuronpedia

    INDEX
    Explanations

    phrases related to philosophical beliefs and societal values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     WATCHED
    -0.82
    Interstitial
    -0.82
    Enlarge
    -0.77
    UX
    -0.77
    HI
    -0.74
    airs
    -0.73
     largeDownload
    -0.73
    NetMessage
    -0.68
    Top
    -0.67
    */(
    -0.66
    POSITIVE LOGITS
    irlf
    0.81
     martyr
    0.80
     mankind
    0.79
     humanity
    0.79
     Christ
    0.79
     simplicity
    0.77
     warfare
    0.77
     Jesus
    0.76
     unity
    0.76
     darkness
    0.75
    Act Density 0.149%

    No Known Activations