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

    Neuronpedia

    INDEX
    Explanations

    references to women and gender issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     înc
    -0.85
     Tare
    -0.84
     kasarigan
    -0.74
    czaj
    -0.68
     flèche
    -0.67
    Dade
    -0.66
    tilles
    -0.66
    кульп
    -0.66
    limus
    -0.66
    })_{
    -0.64
    POSITIVE LOGITS
     women
    1.58
     Women
    1.54
    women
    1.50
    Women
    1.49
     WOMEN
    1.40
    WOMEN
    1.31
     woman
    1.27
     Woman
    1.22
    Woman
    1.18
     WOMAN
    1.17
    Act Density 0.049%

    No Known Activations