INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     in
    -0.08
     the
    -0.07
    essel
    -0.07
     Pitch
    -0.07
    981
    -0.07
     express
    -0.07
    oula
    -0.07
    -0.07
    ဲ့
    -0.07
     photographer
    -0.07
    POSITIVE LOGITS
     уҡы
    0.10
     эшләй
    0.10
     беҙҙең
    0.10
     servants
    0.10
     წავ
    0.09
     яңылыҡтар
    0.09
    ფიქრობ
    0.09
     ფინანს
    0.09
     ალბათ
    0.09
     pisaria
    0.09
    Act Density 0.003%

    No Known Activations