INDEX
    Explanations

    either/whether/depending

    New Auto-Interp
    Negative Logits
    0.36
    OBER
    0.34
     tattoo
    0.34
    以免
    0.33
     dren
    0.33
     这些
    0.33
     এইসব
    0.32
     이런
    0.32
     THESE
    0.32
     illegitimate
    0.32
    POSITIVE LOGITS
     either
    0.89
     entweder
    0.88
    要么
    0.87
     Either
    0.84
    either
    0.82
    Either
    0.81
    Depending
    0.70
     depending
    0.70
     Depending
    0.70
     whether
    0.69
    Act Density 0.598%

    No Known Activations