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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    т
    1.43
    ב
    1.43
    us
    1.41
    يل
    1.36
    ર
    1.36
    ر
    1.35
    其他
    1.25
    ut
    1.24
    у
    1.24
    ز
    1.22
    POSITIVE LOGITS
     in
    1.50
     \
    0.96
    在
    0.95
    renown
    0.86
    <0x80>
    0.85
     ANI
    0.82
     Mighty
    0.80
     OWL
    0.79
     nyata
    0.78
     e
    0.77
    Act Density 0.000%

    No Known Activations