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

    Neuronpedia

    INDEX
    Explanations

    explicit mentions of sexual activity

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BLIC
    -0.82
    REC
    -0.72
     Atmospheric
    -0.70
     Lenn
    -0.69
    IELD
    -0.68
     Bei
    -0.68
     laure
    -0.67
    soType
    -0.66
     citiz
    -0.66
    Ĭ±
    -0.65
    POSITIVE LOGITS
     trafficking
    0.92
    bags
    0.89
    ily
    0.87
    ually
    0.85
    ercise
    0.84
    iest
    0.83
     dolls
    0.82
    addle
    0.82
    ido
    0.81
    bag
    0.79
    Act Density 0.015%

    No Known Activations