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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "rape" or related terms in the context of accusations and discussions surrounding sexual violence

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

    rape and sexual violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Buena
    -0.54
     Motif
    -0.54
     Festi
    -0.50
    Fir
    -0.49
     Helios
    -0.49
     Lottie
    -0.49
     Outsider
    -0.49
    arity
    -0.48
    MCU
    -0.48
    Bü
    -0.48
    POSITIVE LOGITS
     rape
    2.16
     Rape
    1.83
    Rape
    1.77
     raped
    1.76
    rape
    1.68
     raping
    1.67
     rapist
    1.35
     violación
    1.09
     rap
    0.79
     sexual
    0.75
    Act Density 0.003%

    No Known Activations