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

    Neuronpedia

    INDEX
    Explanations

    mentions of close relationships or partnerships, especially involving activities related to crime or shared endeavors

    oai_token-act-pair · gpt-3.5-turbo

    references to partnerships or collaborations involving friends or companions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    limits
    -0.69
    lems
    -0.64
    ynes
    -0.63
    lite
    -0.62
    fter
    -0.61
    :/
    -0.61
    ifact
    -0.60
     dictated
    -0.59
     gates
    -0.59
    cale
    -0.59
    POSITIVE LOGITS
    thood
    0.87
     whom
    0.86
    aukee
    0.81
    sharing
    0.71
    brother
    0.66
     Antioch
    0.66
    acas
    0.65
     BMC
    0.63
     IRC
    0.61
     Wales
    0.61
    Act Density 0.397%

    No Known Activations