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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    elementProp
    0.59
     तपाईं
    0.51
     Configurations
    0.50
     Qué
    0.49
     Są
    0.49
     Що
    0.47
    щего
    0.47
    ましい
    0.47
    형
    0.47
     ebenso
    0.46
    POSITIVE LOGITS
    e
    0.71
    ed
    0.68
    L
    0.61
     pertes
    0.59
    es
    0.56
    ing
    0.55
    them
    0.55
    giers
    0.55
    riminal
    0.55
    several
    0.55
    Act Density 0.000%

    No Known Activations