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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     to
    -0.87
    djangoproject
    -0.75
     לט
    -0.69
     跳转至
    -0.66
     Trondheim
    -0.64
    ribadian
    -0.61
    queryInterface
    -0.61
    to
    -0.61
     berätt
    -0.59
     να
    -0.59
    POSITIVE LOGITS
    RectangleBorder
    0.68
    bolista
    0.65
     contextLoads
    0.65
    érables
    0.65
    GGGG
    0.64
     PAM
    0.60
    $),
    0.59
    rrggbb
    0.59
    ópolis
    0.59
    __()
    0.58
    Act Density 0.022%

    No Known Activations