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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    或是
    0.71
     ataupun
    0.71
     bądź
    0.64
     vagy
    0.63
    或者是
    0.63
    反而
    0.62
    のように
    0.62
     Variant
    0.60
     अथवा
    0.60
     காற்றின்
    0.59
    POSITIVE LOGITS
     includes
    5.33
     include
    5.30
    includes
    4.73
     Includes
    4.62
    Includes
    4.58
    include
    4.56
     incluye
    4.49
     Include
    4.40
     including
    4.38
    包括
    4.32
    Act Density 1.079%

    No Known Activations