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

    Neuronpedia

    INDEX
    Explanations

    symbols and slash characters typically associated with data formatting or structuring in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.88
    ьаж
    -0.81
     للاسماء
    -0.81
    ########.
    -0.80
    ">—
    -0.77
     resourceCulture
    -0.77
    UnusedPrivate
    -0.77
    richTextPanel
    -0.73
     ویکی‌پدی
    -0.72
    -0.72
    POSITIVE LOGITS
    ueil
    0.59
    bited
    0.59
    MEAS
    0.55
    Hoi
    0.53
    raisemb
    0.52
    antd
    0.52
    חר
    0.51
     Mur
    0.50
     decide
    0.50
     Ay
    0.50
    Act Density 0.035%

    No Known Activations