INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Papa
    0.41
    Curve
    0.41
     Pad
    0.39
     Warriors
    0.39
     Punishment
    0.39
    Hitting
    0.39
    Arrows
    0.38
     Torch
    0.38
     warrior
    0.38
    meyer
    0.38
    POSITIVE LOGITS
    powder
    0.58
    ナー
    0.54
    ned
    0.52
     apont
    0.52
    ner
    0.51
    wale
    0.49
    neri
    0.47
    0.47
    ners
    0.46
    нар
    0.46
    Act Density 0.005%

    No Known Activations