INDEX
    Explanations

    phrases related to storytelling and diverse perspectives

    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.10
    3:0.11
    4:0.02
    5:0.04
    6:0.04
    7:0.13
    8:0.23
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
    psey
    -1.34
    wered
    -1.18
    achable
    -1.18
    uffed
    -1.18
    umo
    -1.17
    versible
    -1.12
    approved
    -1.11
    irmed
    -1.07
    iless
    -1.06
    compatible
    -1.06
    POSITIVE LOGITS
     behav
    1.14
     psyche
    1.12
     warr
    1.05
     retina
    1.02
     stranger
    1.02
     Amon
    1.00
     Charm
    0.94
     charact
    0.94
     fandom
    0.93
     monarchy
    0.92
    Act Density 0.053%

    No Known Activations