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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    由于
    0.60
    Because
    0.59
     поскольку
    0.56
    由於
    0.56
    Although
    0.55
    Lorsque
    0.54
    During
    0.53
    because
    0.52
    Before
    0.52
     ponieważ
    0.52
    POSITIVE LOGITS
    ↵
    1.11
     :)
    0.61
     ;)
    0.51
    <0x0D>
    0.51
    ㅎ
    0.46
     ㅋㅋ
    0.46
     =)
    0.46
     :/
    0.44
     (~
    0.42
     xD
    0.42
    Act Density 2.292%

    No Known Activations