INDEX
    Explanations

    instances of interaction and engagement between subjects or entities

    New Auto-Interp
    Negative Logits
       
    -0.19
     Interactive
    -0.18
    venir
    -0.18
     interactive
    -0.18
    Interaction
    -0.17
     interacts
    -0.17
    interaction
    -0.17
     interacting
    -0.17
    Interactive
    -0.17
    interactive
    -0.16
    POSITIVE LOGITS
    ively
    0.27
    ives
    0.26
    iveness
    0.25
    ivate
    0.25
    ed
    0.22
    al
    0.22
    å¼ı
    0.20
    ual
    0.19
    ype
    0.19
    uate
    0.18
    Act Density 0.015%

    No Known Activations