INDEX
    Explanations

    possessive pronouns and their context in sentences

    New Auto-Interp
    Negative Logits
    ej
    -0.20
    eb
    -0.18
     Moody
    -0.17
    ym
    -0.16
    ee
    -0.15
    ep
    -0.14
    umps
    -0.14
    (ir
    -0.14
    ofs
    -0.14
    oc
    -0.14
    POSITIVE LOGITS
    uddenly
    0.18
    rve
    0.15
     own
    0.15
     been
    0.15
    #ad
    0.15
    pter
    0.15
    utow
    0.15
    ifo
    0.15
    ledon
    0.14
    enger
    0.14
    Act Density 0.065%

    No Known Activations