INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.07
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     secondly
    -2.54
    merce
    -2.53
     stems
    -2.25
     areas
    -2.06
     amongst
    -2.06
     aside
    -2.06
     leads
    -2.04
    aganda
    -2.03
     skins
    -1.98
     Bundes
    -1.95
    POSITIVE LOGITS
    itely
    2.58
    cise
    2.40
    Switch
    2.38
    Mouse
    2.33
    lio
    2.30
    rex
    2.26
    Adapt
    2.25
    Iterator
    2.24
    Lear
    2.19
    Change
    2.18
    Act Density 0.000%

    No Known Activations