INDEX
    Explanations

    expressions of desire or intention related to actions and experiences

    New Auto-Interp
    Negative Logits
    izi
    -0.15
     Gore
    -0.14
     Lover
    -0.14
    chio
    -0.14
    4
    -0.14
     Gors
    -0.14
    lep
    -0.13
    umbo
    -0.13
    Ìģ
    -0.13
    ocol
    -0.13
    POSITIVE LOGITS
    oldt
    0.15
    dek
    0.15
    doch
    0.15
    ool
    0.15
    alink
    0.15
    ÏģαÏĤ
    0.14
    @update
    0.14
    ì§ľ
    0.14
    olean
    0.14
    orent
    0.14
    Act Density 0.251%

    No Known Activations