INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    rals
    -0.67
    cffffcc
    -0.63
     Lanka
    -0.62
     loudspe
    -0.62
    anchester
    -0.61
    ndum
    -0.60
     wreck
    -0.60
     adolesc
    -0.59
     Valkyrie
    -0.59
    ADS
    -0.59
    POSITIVE LOGITS
    jet
    1.08
    manship
    0.97
    lings
    0.97
     cartridges
    0.97
     ink
    0.91
    prints
    0.90
    sworth
    0.87
    ling
    0.87
    clip
    0.87
    bowl
    0.86
    Act Density 0.036%

    No Known Activations