INDEX
    Explanations

    intensely emotional or passionate language

    New Auto-Interp
    Negative Logits
    ambda
    -0.16
    orum
    -0.15
    -spacing
    -0.15
    _EST
    -0.14
    uteur
    -0.14
    vez
    -0.14
    ypse
    -0.14
    Prompt
    -0.14
    hea
    -0.14
    plaintext
    -0.14
    POSITIVE LOGITS
    ness
    0.29
     pace
    0.27
     pursuit
    0.24
    -paced
    0.22
    ly
    0.21
     paced
    0.20
    NESS
    0.19
     Pace
    0.18
     nature
    0.18
     attack
    0.17
    Act Density 0.102%

    No Known Activations