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

    Neuronpedia

    INDEX
    Explanations

    numeric dates and birth/death years

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.67
     themſelves
    -0.66
     itſelf
    -0.66
     '\\;'
    -0.62
    aarrggbb
    -0.59
     whoſe
    -0.59
     Monfieur
    -0.58
     Jefus
    -0.57
    GEBURTS
    -0.56
    <bos>
    -0.56
    POSITIVE LOGITS
    ngdoc
    0.59
     Arhivirano
    0.51
    UrlResolution
    0.51
    URIS
    0.50
    archiviato
    0.48
     محفوظة
    0.48
    cipar
    0.48
     décidé
    0.47
    Hauptartikel
    0.46
     Pristupljeno
    0.46
    Act Density 0.007%

    No Known Activations