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

    Neuronpedia

    INDEX
    Explanations

    references to statistical concepts and unknown parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     []:
    -0.57
    upassen
    -0.57
    Véxase
    -0.56
    NOPQRST
    -0.56
    AccessorTable
    -0.55
    ButterKnife
    -0.54
    )':
    -0.54
    ,:);
    -0.53
    akir
    -0.52
    новниш
    -0.51
    POSITIVE LOGITS
    GeneratedCode
    0.56
    Rüyada
    0.55
    nezeu
    0.51
     Económica
    0.51
    jenner
    0.50
    سرائيل
    0.48
    <!--[
    0.47
     olet
    0.47
    Taylor
    0.47
     samarbeid
    0.47
    Act Density 0.111%

    No Known Activations