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

    Neuronpedia

    INDEX
    Explanations

    expressions of tendencies or inclinations, particularly regarding behaviors or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EFIAPI
    -0.71
    UniformLocation
    -0.64
     bénéfice
    -0.61
     Samuels
    -0.60
     kekasih
    -0.58
     Altman
    -0.57
     Donaldson
    -0.57
    gründet
    -0.56
    zeki
    -0.55
    toMatchSnapshot
    -0.55
    POSITIVE LOGITS
     tends
    1.17
     tendency
    1.02
     tende
    0.98
     tend
    0.96
     inclined
    0.94
     tendencies
    0.94
     tienden
    0.92
    Tend
    0.90
     tiende
    0.90
    傾向
    0.90
    Act Density 0.169%

    No Known Activations