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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people in various roles and their actions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.70
    FieldDescriptor
    -0.56
    ætter
    -0.49
     dinam
    -0.49
    раздо
    -0.48
    ________________
    -0.47
     للاسماء
    -0.46
    unhofer
    -0.46
    PropertyChanging
    -0.45
    quées
    -0.45
    POSITIVE LOGITS
    #![
    0.64
    ]');
    0.61
    IsPostBack
    0.60
     autorytatywna
    0.59
     ivelany
    0.59
    /');
    0.57
    ]--;
    0.56
     atof
    0.56
     nargin
    0.54
    новниш
    0.54
    Act Density 0.189%

    No Known Activations