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

    Neuronpedia

    INDEX
    Explanations

    numerical or quantitative information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    basicConfig
    -0.47
     cardin
    -0.47
     reele
    -0.47
     Drapeau
    -0.47
    hland
    -0.47
    kona
    -0.47
    tarea
    -0.46
     minutter
    -0.45
    idl
    -0.45
    clair
    -0.45
    POSITIVE LOGITS
     boarding
    0.77
     homestay
    0.72
    PreferredItem
    0.68
     staying
    0.66
    estay
    0.61
     aceptas
    0.61
     lodging
    0.61
    principalColumn
    0.60
     slee
    0.60
     lodgings
    0.59
    Act Density 0.220%

    No Known Activations