INDEX
    Explanations

    artistic or cultural references, particularly related to specific works and their creators

    New Auto-Interp
    Negative Logits
    ibold
    -0.19
    xBD
    -0.15
    aller
    -0.15
     Tone
    -0.15
     Franken
    -0.14
    TEL
    -0.14
    آ
    -0.14
    ican
    -0.14
    chg
    -0.14
    ernel
    -0.13
    POSITIVE LOGITS
    ector
    0.15
    Ïħν
    0.14
    co
    0.14
    orex
    0.13
    orb
    0.13
     mah
    0.13
    SION
    0.13
    esto
    0.13
     troll
    0.13
    101
    0.13
    Act Density 0.029%

    No Known Activations