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

    Neuronpedia

    INDEX
    Explanations

    mentions of social issues, particularly related to women's rights and healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    êm
    -0.15
    hazi
    -0.15
    beck
    -0.14
    ardy
    -0.14
    nek
    -0.14
    inez
    -0.14
    orte
    -0.14
     bana
    -0.14
    pha
    -0.14
    uc
    -0.14
    POSITIVE LOGITS
     having
    0.19
     personals
    0.19
     who
    0.18
     those
    0.18
     Having
    0.17
     especially
    0.17
     thuá»Ļc
    0.16
    Having
    0.16
     Shall
    0.16
    addtogroup
    0.16
    Act Density 0.272%

    No Known Activations