INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     meringue
    0.46
     muffins
    0.44
     vane
    0.43
     seal
    0.43
     maya
    0.42
     savanna
    0.42
    ע
    0.42
     sage
    0.42
     mortar
    0.42
     meal
    0.41
    POSITIVE LOGITS
    <unused2121>
    0.48
    <unused520>
    0.47
    <unused451>
    0.44
    <unused218>
    0.43
    <unused278>
    0.43
    <unused399>
    0.43
    <unused645>
    0.42
    <unused734>
    0.42
    <unused729>
    0.42
    <unused341>
    0.42
    Act Density 0.448%

    No Known Activations