INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    vier
    -0.75
    agall
    -0.72
    arette
    -0.72
    hap
    -0.71
    abis
    -0.68
    imaru
    -0.67
    isner
    -0.67
    yss
    -0.67
    Ĭ±
    -0.66
    ŃĶ
    -0.65
    POSITIVE LOGITS
     Loading
    0.96
     clip
    0.78
     clips
    0.76
     footage
    0.74
     snippet
    0.74
     Transcript
    0.72
     Surveillance
    0.71
     Tutorial
    0.71
    clip
    0.68
    =>
    0.68
    Act Density 0.035%

    No Known Activations