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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ti
    0.48
    כ
    0.47
    utis
    0.47
    ir
    0.46
    lä
    0.46
    men
    0.45
    y
    0.45
    א
    0.45
    ä
    0.45
    use
    0.45
    POSITIVE LOGITS
    どり
    0.45
    mybatis
    0.44
    ﺲ
    0.44
     poteva
    0.42
     ..$
    0.42
    뜸
    0.42
     firepower
    0.42
     decisão
    0.41
     pianta
    0.41
     ….
    0.40
    Act Density 0.006%

    No Known Activations