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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     It
    0.72
     it
    0.64
     I
    0.51
    ’
    0.46
    มัน
    0.40
    攽
    0.39
     มัน
    0.38
    It
    0.37
    んですね
    0.36
     can
    0.36
    POSITIVE LOGITS
    3
    0.76
    ك
    0.71
    4
    0.69
    6
    0.68
    0
    0.63
    5
    0.61
    9
    0.54
    ка
    0.53
    1
    0.52
    were
    0.51
    Act Density 0.000%

    No Known Activations