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

    Neuronpedia

    INDEX
    Explanations

    references to figures, tables, or illustrations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    المناصب
    -0.77
    Hentet
    -0.73
     estekak
    -0.69
    TagMode
    -0.66
    $.
    -0.62
     hanem
    -0.61
     تانيه
    -0.60
    rzez
    -0.59
    .",
    -0.58
    הערות
    -0.58
    POSITIVE LOGITS
     تضيفلها
    0.71
    </
    0.66
    awtextra
    0.63
    entrySet
    0.62
    Personendaten
    0.61
    BeginInit
    0.60
    chyma
    0.59
    Ec
    0.54
     (°
    0.54
    ✭✭
    0.54
    Act Density 0.786%

    No Known Activations