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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that appear to be formatted as tags or markup

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.94
    WebControls
    -0.93
     समीक्षक
    -0.73
    DockStyle
    -0.69
     gawas
    -0.69
     الحره
    -0.68
     يتيمه
    -0.67
    styleType
    -0.66
    principalTable
    -0.65
     MonoBehaviour
    -0.65
    POSITIVE LOGITS
    my
    0.53
    об
    0.52
    Commons
    0.51
    ELEM
    0.50
    あとは
    0.49
    ِّ
    0.49
    awaiter
    0.48
    trice
    0.47
    olí
    0.46
    浅
    0.46
    Act Density 0.008%

    No Known Activations