INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     barat
    1.01
     diri
    0.95
     zich
    0.91
     bert
    0.89
    𝑚
    0.88
    ことになる
    0.88
    时候
    0.87
    شوند
    0.86
    വധി
    0.85
    amiento
    0.85
    POSITIVE LOGITS
     jumping
    1.30
     Jump
    1.24
    1.23
     leaps
    1.20
     jump
    1.20
    Jump
    1.19
    scotch
    1.17
    jumping
    1.16
    jump
    1.15
    obstacles
    1.14
    Act Density 0.050%

    No Known Activations