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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ية
    1.60
    és
    0.98
    0.98
     It
    0.95
    ють
    0.94
    ία
    0.91
    е
    0.90
     If
    0.89
    inks
    0.87
    э
    0.87
    POSITIVE LOGITS
     to
    1.41
    ED
    1.32
    ש
    1.29
    ম
    1.28
    DA
    1.27
     the
    1.27
    ,
    1.24
    ;
    1.24
     by
    1.23
    ON
    1.23
    Act Density 0.000%

    No Known Activations