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

    Neuronpedia

    INDEX
    Explanations

    references to women or discussions surrounding women's issues and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laje
    -0.59
    父の
    -0.55
    хоз
    -0.54
     parental
    -0.53
    tablir
    -0.50
    atic
    -0.49
    ดิน
    -0.49
     bedrijfs
    -0.49
     terrestres
    -0.49
    рный
    -0.47
    POSITIVE LOGITS
     women
    3.70
     Women
    3.40
    Women
    3.32
    women
    3.30
     WOMEN
    3.11
    WOMEN
    2.83
     woman
    2.33
     womens
    2.23
     Woman
    2.21
    Woman
    2.09
    Act Density 0.078%

    No Known Activations