INDEX
    Explanations

    phrases and words associated with grief and mourning.

    The neuron detects words related to the process of grieving or loss (e.g. grieve, grieving, grief, loss).

    New Auto-Interp
    Negative Logits
     casing
    -0.07
     Clint
    -0.07
     Analog
    -0.06
     commercially
    -0.06
     Chip
    -0.06
     tech
    -0.06
     Initializing
    -0.06
    ΑΝΤ
    -0.06
     فنی
    -0.06
    .Ad
    -0.06
    POSITIVE LOGITS
     grief
    0.11
     mourning
    0.10
     grieving
    0.10
     mourn
    0.08
    geb
    0.07
     woes
    0.07
    rieved
    0.07
     pe
    0.07
     mour
    0.06
     worrying
    0.06
    Act Density 0.005%

    No Known Activations