INDEX
    Explanations

    the substring "ent" in words

    New Auto-Interp
    Negative Logits
    eneg
    -0.17
     Barrel
    -0.16
    isia
    -0.15
    .si
    -0.15
    á»ģ
    -0.15
     barrel
    -0.14
    ikan
    -0.14
    endants
    -0.14
    rol
    -0.14
     McCart
    -0.14
    POSITIVE LOGITS
    llen
    0.14
    tet
    0.14
    dock
    0.14
    OfWork
    0.14
    iten
    0.14
     Bers
    0.14
    pered
    0.13
    orrow
    0.13
    .deploy
    0.13
    rede
    0.13
    Act Density 0.000%

    No Known Activations