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

    Neuronpedia

    INDEX
    Explanations

    numeric values representing quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.59
    Rüyada
    -0.43
     EnglishChoose
    -0.42
     Empieza
    -0.41
    kezett
    -0.41
    Rohy
    -0.39
    dientemente
    -0.37
    consulté
    -0.37
    وقات
    -0.36
    жливо
    -0.36
    POSITIVE LOGITS
     Twenty
    1.76
     Twelve
    1.75
     Eight
    1.75
    Five
    1.73
     Sixteen
    1.73
     Five
    1.72
     Fourteen
    1.72
     Seven
    1.71
    Seven
    1.70
    Eight
    1.70
    Act Density 1.017%

    No Known Activations