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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "nation" or "national."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Amos
    -0.85
     Candel
    -0.82
    amental
    -0.81
    іга
    -0.81
     Kinh
    -0.80
    संद
    -0.80
    ionali
    -0.80
     Bep
    -0.80
    ourable
    -0.79
     Morm
    -0.79
    POSITIVE LOGITS
    a
    1.14
     nations
    0.98
     Nations
    0.96
     Kass
    0.89
    aData
    0.84
    Nations
    0.81
     naciones
    0.79
     Nation
    0.78
    aA
    0.77
     Nationen
    0.77
    Act Density 0.130%

    No Known Activations