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

    Neuronpedia

    INDEX
    Explanations

    the interactions and relationships between variables in a data set

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.84
    InjectAttribute
    -0.79
    SequentialGroup
    -0.79
     GenerationType
    -0.73
    Hozzáférés
    -0.62
     Meksiku
    -0.62
    ⓧ
    -0.62
    AddHtmlAttribute
    -0.61
    ViewFeatures
    -0.61
     createState
    -0.61
    POSITIVE LOGITS
    出版年
    0.59
     sou
    0.47
     coming
    0.47
    skine
    0.46
    hon
    0.46
    spar
    0.46
    teen
    0.46
    ściu
    0.45
    adomo
    0.45
    enzie
    0.45
    Act Density 0.231%

    No Known Activations