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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authority and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.84
    __*/
    -0.77
    Personendaten
    -0.72
     newOwner
    -0.68
    InputBorder
    -0.68
    __(/*!
    -0.67
    دانشنامهٔ
    -0.67
     Мексичка
    -0.66
    RectangleBorder
    -0.66
    findpost
    -0.66
    POSITIVE LOGITS
    ↵
    0.27
     ac
    0.27
     diss
    0.26
    <eos>
    0.25
     barang
    0.24
    特
    0.24
     bague
    0.23
    :
    0.23
     terper
    0.23
     bag
    0.23
    Act Density 0.758%

    No Known Activations