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

    Neuronpedia

    INDEX
    Explanations

    references to gaining immunity or leniency from accountability

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

    act with impunity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pakk
    -0.39
    Principal
    -0.38
    おはようございます
    -0.38
     kitabı
    -0.37
     lisesi
    -0.36
    ToProps
    -0.36
     uppgifter
    -0.36
    OLAR
    -0.35
     Relaciones
    -0.35
     läsa
    -0.35
    POSITIVE LOGITS
     impunity
    0.69
     tolerated
    0.66
    addGap
    0.62
     tolerable
    0.58
    aarrggbb
    0.57
    Diweddarwch
    0.57
     undetected
    0.57
     Allowed
    0.56
     tolerate
    0.56
     وتسجيلات
    0.55
    Act Density 0.035%

    No Known Activations