INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    avg
    -0.07
     зап
    -0.06
    aktion
    -0.06
    cat
    -0.06
    ΐ
    -0.06
    ³
    -0.06
     userName
    -0.06
    gather
    -0.06
    goals
    -0.06
    -score
    -0.05
    POSITIVE LOGITS
    MZ
    0.08
     transcription
    0.08
    )NULL
    0.07
     NVIC
    0.07
    MRI
    0.06
    VILLE
    0.06
     bookstore
    0.06
     bh
    0.06
    _wrong
    0.06
     kaps
    0.06
    Act Density 0.007%

    No Known Activations