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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ñıке
    -0.17
     коÑĤоÑĢое
    -0.16
     ÙħÙĨÙĩا
    -0.15
     αÏħÏĦά
    -0.13
    à¸ļรร
    -0.13
    uibModal
    -0.13
    ãģ¯ãģªãģĦ
    -0.13
     mÄĽlo
    -0.12
     بÙĪابة
    -0.12
    ëħĦìĹIJëĬĶ
    -0.12
    POSITIVE LOGITS
     who
    1.39
     whom
    1.20
    who
    1.17
     Who
    0.86
     whose
    0.85
     quien
    0.85
    Who
    0.82
     kteÅĻÃŃ
    0.72
     quienes
    0.72
     qui
    0.72
    Act Density 1.589%

    No Known Activations