INDEX
    Explanations

    names of historical figures or species related to specific contexts

    New Auto-Interp
    Negative Logits
    etto
    -0.16
    kiem
    -0.15
    ondo
    -0.15
    cip
    -0.15
    zzo
    -0.15
    .BLL
    -0.14
     bekl
    -0.14
    asco
    -0.14
    abay
    -0.14
    erno
    -0.14
    POSITIVE LOGITS
    ery
    0.16
    ERY
    0.15
    estr
    0.14
    éry
    0.14
    .Formatter
    0.13
    .scalablytyped
    0.13
    clin
    0.13
    ген
    0.13
    éĥİ
    0.13
    baum
    0.13
    Act Density 0.004%

    No Known Activations