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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating previous research or findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.55
     nonetheless
    -0.53
     Yale
    -0.52
    <bos>
    -0.51
     alc
    -0.51
    megen
    -0.50
     nevertheless
    -0.48
    AddWithValue
    -0.48
     мебели
    -0.48
    zwald
    -0.48
    POSITIVE LOGITS
    webElementXpaths
    0.87
     للاسماء
    0.85
    ISupport
    0.81
    Personendaten
    0.77
    Werdegang
    0.72
     <<<<<<<<<<<<<<
    0.71
     initComponents
    0.71
     évidence
    0.70
     Paglinawan
    0.70
     autorytatywna
    0.69
    Act Density 0.034%

    No Known Activations