INDEX
    Explanations

    expressions of love and passion for various activities and interests

    New Auto-Interp
    Negative Logits
    ocos
    -0.15
    apore
    -0.13
    ogr
    -0.13
    wahl
    -0.13
    ilded
    -0.13
    ulk
    -0.13
    人æ°Ĺ
    -0.13
    odes
    -0.13
    opies
    -0.13
     responses
    -0.12
    POSITIVE LOGITS
     anything
    0.24
    anything
    0.19
     horses
    0.19
     animals
    0.18
     cars
    0.18
     books
    0.18
     gadgets
    0.17
     dogs
    0.17
    birds
    0.17
     motorcycles
    0.17
    Act Density 0.245%

    No Known Activations