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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    は約
    0.63
    ah
    0.63
     ม
    0.63
    れない
    0.61
     figlia
    0.61
    れません
    0.60
    を買
    0.60
    ammlung
    0.59
     jum
    0.59
     Unpublished
    0.59
    POSITIVE LOGITS
    ли
    0.88
    ни
    0.83
    ون
    0.82
     ergonomics
    0.76
    ור
    0.72
    т
    0.71
    ле
    0.71
    ش
    0.68
    ס
    0.68
    ри
    0.67
    Act Density 8.543%

    No Known Activations