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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     올해
    1.25
     Pire
    1.23
     ஆண்டு
    1.19
    톄
    1.17
    两年
    1.14
    zor
    1.14
     instit
    1.13
    년에
    1.12
     deadliest
    1.12
    bender
    1.09
    POSITIVE LOGITS
    سلام
    1.16
     rangement
    0.99
    お客様
    0.95
    theless
    0.94
     números
    0.94
     nét
    0.93
     DETAILS
    0.92
     claridad
    0.90
     tokens
    0.88
    భ్య
    0.88
    Act Density 0.334%

    No Known Activations