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

    Neuronpedia

    INDEX
    Explanations

    words related to wisdom and knowledge

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    外部リンク
    -0.69
     ویکی‌پدی
    -0.67
    ########.
    -0.67
    teilung
    -0.66
    AccessorTable
    -0.66
    Примітки
    -0.65
    ьаж
    -0.65
     Chamb
    -0.64
    rophilic
    -0.62
    laund
    -0.62
    POSITIVE LOGITS
     Wiseman
    1.18
     Wisdom
    1.15
     wisdom
    1.09
     Wise
    1.08
    Wisdom
    1.05
     Wis
    1.04
     wise
    1.02
     WISE
    1.00
     WIS
    0.98
     SAGE
    0.93
    Act Density 0.005%

    No Known Activations