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

    Neuronpedia

    INDEX
    Explanations

    words related to sexual misconduct and inappropriate behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual misconduct and assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AY
    -0.76
    IVERS
    -0.76
    IPS
    -0.70
    REL
    -0.68
    ICA
    -0.66
    selves
    -0.65
    oak
    -0.65
    iets
    -0.64
    eli
    -0.64
    quickShipAvailable
    -0.64
    POSITIVE LOGITS
     grop
    1.14
    Sexual
    1.07
     sexually
    1.02
     inappropriately
    1.00
     assaulted
    0.99
     mol
    0.98
     allegations
    0.96
     lewd
    0.94
     rape
    0.92
     raping
    0.89
    Act Density 0.130%

    No Known Activations