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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public statements or declarations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     bianchi
    -0.63
    sieur
    -0.61
     rossi
    -0.61
     koc
    -0.60
     maroc
    -0.59
     bronz
    -0.58
     babi
    -0.58
     ananas
    -0.58
     lele
    -0.57
     lampe
    -0.56
    POSITIVE LOGITS
    Mə
    0.69
    Mitä
    0.64
     autorytatywna
    0.63
    Manbalar
    0.62
    Și
    0.60
    Să
    0.59
    webElementXpaths
    0.59
    pueden
    0.58
     disambiguazione
    0.58
    Răsp
    0.58
    Act Density 0.573%

    No Known Activations