INDEX
    Explanations

    terms related to medicinal and therapeutic substances

    New Auto-Interp
    Negative Logits
    indre
    -0.15
    ãĥķãĤ
    -0.15
    olg
    -0.15
    avra
    -0.14
    butt
    -0.14
    ..↵↵↵↵
    -0.14
     Dich
    -0.14
    iyim
    -0.14
    infra
    -0.14
    ammad
    -0.14
    POSITIVE LOGITS
    ¯
    0.19
    ĥ
    0.18
    ãĢħ
    0.17
    Į
    0.16
    aps
    0.15
    ic
    0.15
    icot
    0.15
    ľ
    0.14
    Gen
    0.14
     merc
    0.14
    Act Density 0.007%

    No Known Activations