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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that convey comparisons and evaluations of individuals or groups, particularly in relation to social or personal attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilian
    -0.21
     civilians
    -0.18
     vrouw
    -0.16
    frauen
    -0.16
     vrouwen
    -0.15
    vero
    -0.15
    ufen
    -0.15
    _UNICODE
    -0.15
     Frauen
    -0.15
     women
    -0.15
    POSITIVE LOGITS
    ä¸Ī夫
    0.20
     males
    0.20
    éĽĦ
    0.20
     masculine
    0.20
     male
    0.20
     Ñĩолов
    0.18
    male
    0.17
    ová
    0.17
    à¸Ļาย
    0.16
     Husband
    0.16
    Act Density 1.699%

    No Known Activations