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

    Neuronpedia

    INDEX
    Explanations

    words related to sexual misconduct and abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual misconduct and related accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVERS
    -0.75
     pessim
    -0.71
    alg
    -0.70
     EntityItem
    -0.67
    DIT
    -0.67
    ciation
    -0.67
    icip
    -0.66
    addons
    -0.63
     Effective
    -0.63
    anke
    -0.63
    POSITIVE LOGITS
     underage
    1.25
     inappropriately
    1.20
     sexually
    1.18
     grop
    1.14
     minors
    1.10
     prostitutes
    1.04
    Sexual
    1.04
     genitals
    1.03
     sexual
    1.03
     lewd
    0.98
    Act Density 0.266%

    No Known Activations