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

    Neuronpedia

    INDEX
    Explanations

    references to women and discussions around gender issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     înc
    -0.78
    czaj
    -0.69
    limus
    -0.68
     Idy
    -0.68
    URLException
    -0.67
    AndEndTag
    -0.65
    кульп
    -0.62
    Dade
    -0.62
    paramInt
    -0.61
     Tare
    -0.60
    POSITIVE LOGITS
     women
    2.81
     Women
    2.67
    Women
    2.57
    women
    2.50
     WOMEN
    2.44
    WOMEN
    2.27
     woman
    1.98
     womens
    1.94
     Woman
    1.94
     Womens
    1.83
    Act Density 0.063%

    No Known Activations