INDEX
    Explanations

    actions related to aggression and violence, particularly in interpersonal relationships

    New Auto-Interp
    Negative Logits
    anders
    -0.19
    ono
    -0.15
    851
    -0.15
    åĨĬ
    -0.15
    aiser
    -0.15
    ongo
    -0.15
    èĪĪ
    -0.14
    (rawValue
    -0.14
    unc
    -0.14
    APPER
    -0.14
    POSITIVE LOGITS
     anyone
    0.27
     anybody
    0.26
     somebody
    0.26
     someone
    0.25
     him
    0.24
     everybody
    0.24
     everyone
    0.24
     us
    0.23
     them
    0.23
     people
    0.21
    Act Density 0.520%

    No Known Activations