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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt or questioning authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĨе
    -0.17
    ATAR
    -0.15
    ianne
    -0.14
     Folk
    -0.14
     paylaÅŁ
    -0.14
    ért
    -0.13
     Dickinson
    -0.13
    mür
    -0.13
     Nun
    -0.13
     folk
    -0.13
    POSITIVE LOGITS
    /player
    0.15
    oggles
    0.14
    arda
    0.14
    èĮĤ
    0.13
    Dragon
    0.13
     LSB
    0.13
    loha
    0.13
     lanes
    0.13
    iesel
    0.13
    ahn
    0.13
    Act Density 0.109%

    No Known Activations