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

    Neuronpedia

    INDEX
    Explanations

    elements related to significant events or anniversaries in history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SEDS
    -0.80
    Билгалдахарш
    -0.72
    IntoConstraints
    -0.71
     esternos
    -0.70
     дописавши
    -0.70
     pinulongan
    -0.67
     ostavi
    -0.67
    lujah
    -0.65
     Chwiliwch
    -0.65
    fopen
    -0.64
    POSITIVE LOGITS
    년
    0.51
    years
    0.49
     года
    0.49
    year
    0.49
     year
    0.49
     Тогда
    0.48
     року
    0.48
     cấp
    0.48
    年
    0.48
     lalu
    0.47
    Act Density 0.652%

    No Known Activations