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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    1.10
    .--
    1.09
     изделий
    1.00
    plications
    0.99
     manualmente
    0.97
    ..--
    0.96
     thereby
    0.96
    .${
    0.96
    美丽的
    0.95
    --
    0.94
    POSITIVE LOGITS
    ترنت
    1.04
     metre
    1.04
    एस
    1.02
     focus
    0.99
    뱀
    0.99
    ি
    0.95
     hope
    0.95
    verage
    0.94
     trek
    0.93
     Mama
    0.92
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.