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

    Neuronpedia

    INDEX
    Explanations

    the name "Karen" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Karen and Kare variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fü
    -0.34
    zhi
    -0.33
    tp
    -0.33
    zio
    -0.32
    submit
    -0.31
    PRIMARY
    -0.31
    オ
    -0.31
     Muhamma
    -0.31
    扁
    -0.30
     пра
    -0.30
    POSITIVE LOGITS
     Karen
    2.22
    Karen
    2.09
    karen
    1.62
     karen
    1.59
     Kare
    1.13
    Kare
    1.05
    kare
    0.92
     kare
    0.90
     Karin
    0.86
    Karin
    0.81
    Act Density 0.003%

    No Known Activations