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

    Neuronpedia

    INDEX
    Explanations

    references to women and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]==
    -0.56
     ==
    -0.52
    childs
    -0.50
     Pfalz
    -0.50
    )==
    -0.50
     Kamp
    -0.47
     Garfield
    -0.47
    žnost
    -0.47
    ==
    -0.47
     Chamb
    -0.46
    POSITIVE LOGITS
    WOMEN
    0.68
     ویکی‌پدی
    0.63
    0.60
    TestingModule
    0.58
     nonUne
    0.57
    lehem
    0.56
    getChildren
    0.56
     women
    0.56
     EventEmitter
    0.56
    women
    0.56
    Act Density 0.146%

    No Known Activations