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

    Neuronpedia

    INDEX
    Explanations

    numerical data, specifically years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -1.18
     فريبيس
    -0.77
     ModelExpression
    -0.76
    tanleria
    -0.75
     estekak
    -0.73
     dAtA
    -0.73
    fjspx
    -0.71
    thâu
    -0.69
     comuniques
    -0.69
     ModelRenderer
    -0.67
    POSITIVE LOGITS
    olyte
    0.56
     umana
    0.54
     publiques
    0.51
    gapi
    0.51
    ↵↵
    0.49
     emprunt
    0.49
     vectorielles
    0.48
    مصادر
    0.48
     marins
    0.47
     culturali
    0.47
    Act Density 0.100%

    No Known Activations