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

    Neuronpedia

    INDEX
    Explanations

    references to sexual content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sexual relationships or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BLIC
    -0.76
    ģĸ
    -0.76
    £ı
    -0.73
    Ĭ±
    -0.72
     retri
    -0.69
    REC
    -0.69
    ¶ħ
    -0.67
     Lenn
    -0.67
     citiz
    -0.66
    EMP
    -0.66
    POSITIVE LOGITS
    ido
    0.95
    ily
    0.88
    iest
    0.86
    ually
    0.86
     trafficking
    0.85
    bags
    0.82
    liest
    0.82
    addle
    0.81
    iness
    0.79
    bag
    0.75
    Act Density 0.016%

    No Known Activations