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

    Neuronpedia

    INDEX
    Explanations

    explicit references to sexual activities and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.72
     surla
    -0.69
    IonicModule
    -0.69
    awtextra
    -0.61
    FailureListener
    -0.61
     للاسماء
    -0.60
     superstitious
    -0.60
    épendant
    -0.58
    fromnode
    -0.58
     aikaa
    -0.57
    POSITIVE LOGITS
     sexual
    0.98
     sex
    0.89
     Sexual
    0.86
     seks
    0.83
    Sexual
    0.81
     SEX
    0.80
    🔞
    0.78
     sexually
    0.77
     sexo
    0.76
     erotic
    0.75
    Act Density 0.340%

    No Known Activations