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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advices or directives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ario
    -0.70
     notwithstanding
    -0.64
     Donation
    -0.62
     disposed
    -0.59
    icious
    -0.59
    hunt
    -0.59
    max
    -0.58
     condem
    -0.58
    etermination
    -0.58
    rador
    -0.57
    POSITIVE LOGITS
     humanity
    0.72
     us
    0.72
     our
    0.71
     humankind
    0.70
    them
    0.69
    their
    0.69
     those
    0.66
    those
    0.66
     these
    0.66
     them
    0.62
    Act Density 0.117%

    No Known Activations