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

    Neuronpedia

    INDEX
    Explanations

    references to attractiveness and sexual appeal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.55
    tagHelperRunner
    -0.54
     NSCoder
    -0.51
     OnEnable
    -0.50
    cadeira
    -0.46
    -0.45
    openzeppelin
    -0.45
     Obrador
    -0.45
     تعدى
    -0.43
     program
    -0.43
    POSITIVE LOGITS
     sexy
    0.67
     attractiveness
    0.64
     attractive
    0.63
     alluring
    0.61
     seductive
    0.57
    sexy
    0.53
     beauty
    0.51
     seksi
    0.51
     allure
    0.50
     Attractive
    0.50
    Act Density 0.206%

    No Known Activations