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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ,
    1.38
     ,
    0.99
    0.92
    、
    0.86
     a
    0.83
    .
    0.82
    -,
    0.80
    (
    0.79
    í
    0.78
    ย
    0.78
    POSITIVE LOGITS
     এমনকি
    1.01
     hatta
    0.99
     навіть
    0.97
    甚至是
    0.94
    そして
    0.93
     bahkan
    0.90
    甚至
    0.88
     downright
    0.86
     সর্বো
    0.85
    等方面
    0.85
    Act Density 0.008%

    No Known Activations