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

    Neuronpedia

    INDEX
    Explanations

    references to fixes and updates in software

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.77
     myſelf
    -0.75
     purpoſe
    -0.73
     ſtill
    -0.73
     Mahomet
    -0.73
     урна
    -0.73
    dymyr
    -0.71
     ſever
    -0.70
     pleaſure
    -0.69
     himſelf
    -0.69
    POSITIVE LOGITS
    XmlAccessType
    0.48
    routeProvider
    0.47
    labelledby
    0.46
     mannen
    0.46
    ,
    0.46
     ayudó
    0.43
     ayud
    0.43
     patří
    0.43
     désolés
    0.43
    Sprintf
    0.42
    Act Density 0.007%

    No Known Activations