INDEX
    Explanations

    expressions of intense emotion, particularly related to screaming

    loud vocalizations of emotion

    New Auto-Interp
    Negative Logits
     Dory
    -0.48
     minor
    -0.47
     Minor
    -0.47
     Firm
    -0.46
     DPD
    -0.45
     Handler
    -0.43
     Dili
    -0.43
     Janus
    -0.43
     Amity
    -0.43
    }}%
    -0.42
    POSITIVE LOGITS
     scream
    1.84
     screaming
    1.66
     screamed
    1.58
     Scream
    1.55
     screams
    1.54
    scream
    1.54
    Scream
    1.52
    Scre
    1.20
     Scre
    1.12
    scre
    1.09
    Act Density 0.002%

    No Known Activations