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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preferences or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NamedQueries
    -0.62
     tratt
    -0.61
    SizeF
    -0.61
    XmlAccessType
    -0.59
    RectangleBorder
    -0.59
    getDoctrine
    -0.58
     næ
    -0.52
    Pure
    -0.51
    viewDidLoad
    -0.51
     сме
    -0.51
    POSITIVE LOGITS
     gustaría
    0.95
     gostaria
    0.94
    aimerais
    0.81
     souhaite
    0.70
    openzeppelin
    0.69
    kháu
    0.69
    Teles
    0.68
     Kindly
    0.67
    Assistance
    0.67
    MLLoader
    0.67
    Act Density 0.049%

    No Known Activations