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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the occurrence of events for the first time

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     maji
    -0.57
    iomanip
    -0.49
     maj
    -0.47
     gotten
    -0.47
    llingen
    -0.47
    zia
    -0.47
    ginfo
    -0.47
    Bu
    -0.46
    sS
    -0.44
    லி
    -0.44
    POSITIVE LOGITS
    Personensuche
    1.00
    ReusableCell
    0.89
    GEBURTSDATUM
    0.83
    Билгалдахарш
    0.81
    ModelSerializer
    0.79
    kháu
    0.79
    HasColumnName
    0.75
    InputBorder
    0.74
    thâu
    0.74
     ModelRenderer
    0.74
    Act Density 0.006%

    No Known Activations