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

    Neuronpedia

    INDEX
    Explanations

    references to tables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.83
     Gegenteil
    -0.80
    Aure
    -0.73
    orianCalendar
    -0.72
     مرئيه
    -0.72
     Hệ
    -0.72
    printStackTrace
    -0.68
     couverts
    -0.67
    epar
    -0.65
    lač
    -0.64
    POSITIVE LOGITS
     tbl
    1.20
    tbl
    1.18
     Robyn
    0.72
     Kuru
    0.72
    Cyfeiriadau
    0.71
     Khu
    0.69
     Tigre
    0.65
    Robyn
    0.65
    FTE
    0.65
        
    0.64
    Act Density 0.003%

    No Known Activations