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

    Neuronpedia

    INDEX
    Explanations

    words indicating conditions or factors associated with processes and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    siella
    -0.52
    WillAppear
    -0.50
     ?>>
    -0.49
    bata
    -0.49
     changeable
    -0.48
    InstanceState
    -0.48
     RO
    -0.48
    RegisterType
    -0.48
    ylla
    -0.47
     useAppContext
    -0.47
    POSITIVE LOGITS
    featureID
    0.81
     becauſe
    0.68
    WebServlet
    0.66
    tonode
    0.62
    AndEndTag
    0.62
     TextAppearance
    0.59
     disparu
    0.59
    ViewFeatures
    0.58
    roidery
    0.58
     >=",
    0.57
    Act Density 0.557%

    No Known Activations