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

    Neuronpedia

    INDEX
    Explanations

    words indicating permission or enablement

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     بيها
    -0.82
    Ena
    -0.69
     able
    -0.68
     onts
    -0.68
    出版年
    -0.66
     cister
    -0.66
     Pemberton
    -0.66
    Pl
    -0.66
    ec
    -0.65
     fortæ
    -0.65
    POSITIVE LOGITS
    allowance
    0.81
     allowances
    0.77
    lammatory
    0.73
     Allowance
    0.73
     Paglinawan
    0.73
    InjectMocks
    0.69
    RenderAtEndOf
    0.69
     allowance
    0.68
    basicConfig
    0.68
    assum
    0.67
    Act Density 0.032%

    No Known Activations