INDEX
    Explanations

    terms related to trauma and mental health conditions

    New Auto-Interp
    Negative Logits
    undler
    -0.15
     åĸ
    -0.15
    ocaly
    -0.15
     Kl
    -0.15
    ighton
    -0.15
     Burgess
    -0.14
    akk
    -0.14
    oda
    -0.14
    oker
    -0.14
    aked
    -0.14
    POSITIVE LOGITS
    cape
    0.15
    aisy
    0.15
    /kernel
    0.14
     cap
    0.14
     Drum
    0.14
     Walt
    0.13
    .plist
    0.13
     تج
    0.13
    jis
    0.13
    washer
    0.13
    Act Density 0.096%

    No Known Activations