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

    Neuronpedia

    INDEX
    Explanations

    dates and time periods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    parency
    -0.73
    hedral
    -0.72
    ioned
    -0.71
    olves
    -0.71
    holder
    -0.69
    Kin
    -0.68
    hyde
    -0.67
    anamo
    -0.67
    ramer
    -0.67
    player
    -0.66
    POSITIVE LOGITS
     1936
    0.79
     onwards
    0.78
     1938
    0.76
     Osw
    0.72
    å¹
    0.72
     1934
    0.72
    keley
    0.70
    çļ
    0.70
     1939
    0.69
     1946
    0.68
    Act Density 3.496%

    No Known Activations