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

    Neuronpedia

    INDEX
    Explanations

    references to historical practices and concepts involving gender roles and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.69
     himſelf
    -0.63
     myſelf
    -0.61
     Monfieur
    -0.61
     quæ
    -0.61
     Efq
    -0.60
     Jefus
    -0.58
     juſt
    -0.58
     transfieras
    -0.55
     houſe
    -0.55
    POSITIVE LOGITS
    曖昧さ回避
    0.53
    Biblia
    0.49
    ertale
    0.48
    Citations
    0.48
    raisers
    0.48
    SGS
    0.48
    CardBody
    0.47
     mum
    0.46
    yaar
    0.46
    ']).
    0.46
    Act Density 0.514%

    No Known Activations