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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     اپنی
    0.84
     respectivos
    0.81
    𝓐
    0.78
    अपनी
    0.76
     respective
    0.73
    人了
    0.72
    自己的
    0.72
    respective
    0.71
     belieb
    0.71
     அவர்களுடைய
    0.70
    POSITIVE LOGITS
     only
    1.06
     is
    0.92
     there
    0.86
     Only
    0.86
    only
    0.81
     There
    0.80
    目的是
    0.77
     chỉ
    0.75
     isn
    0.73
     только
    0.71
    Act Density 0.171%

    No Known Activations