INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    MU
    -0.09
    なら
    -0.08
    RO
    -0.08
     Emery
    -0.08
    orton
    -0.07
    -0.07
    -hard
    -0.07
    -0.07
     Harding
    -0.07
     MIL
    -0.07
    POSITIVE LOGITS
     captured
    0.12
    Captured
    0.11
     capturing
    0.09
     പിട
    0.09
    capture
    0.09
     Capture
    0.08
    akespe
    0.08
    captures
    0.08
     linguistic
    0.08
    Capture
    0.08
    Act Density 0.003%

    No Known Activations