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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical analysis and refutation in a political context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.07
    OnEvent
    -0.61
    openModal
    -0.60
     inev
    -0.56
     disagre
    -0.55
     cuck
    -0.55
    closeConnection
    -0.55
    Yess
    -0.55
    UwU
    -0.54
    Hahah
    -0.54
    POSITIVE LOGITS
     CiNii
    0.87
     truk
    0.72
     akku
    0.69
     puto
    0.67
     fasi
    0.67
     mahd
    0.66
     estekak
    0.65
     lapto
    0.64
     maksi
    0.63
     Église
    0.63
    Act Density 0.425%

    No Known Activations