INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     overwhelming
    -0.73
    ADRA
    -0.70
    Tokens
    -0.70
    PASS
    -0.67
    FACE
    -0.64
    Vote
    -0.61
    Scotland
    -0.60
    Region
    -0.59
    Issue
    -0.59
    Story
    -0.58
    POSITIVE LOGITS
    oglu
    1.23
    oulos
    1.16
    opoulos
    1.15
    ski
    1.13
    icz
    1.11
    tein
    1.10
    ewski
    1.10
     Jr
    1.09
    zyk
    1.05
    iewicz
    1.03
    Act Density 0.403%

    No Known Activations