INDEX
    Explanations

    instances of the word "striking" and its derivatives

    New Auto-Interp
    Negative Logits
    çŃĭ
    -0.16
    cock
    -0.15
    ogue
    -0.15
    legg
    -0.15
    enet
    -0.15
     spur
    -0.15
    kir
    -0.14
    ctic
    -0.14
    doch
    -0.14
    acre
    -0.13
    POSITIVE LOGITS
    uben
    0.15
    олÑĮно
    0.14
    /sh
    0.14
    out
    0.14
    setup
    0.14
    å¢ĥ
    0.14
     LICENSE
    0.14
     Gard
    0.13
     Gone
    0.13
    al
    0.13
    Act Density 0.024%

    No Known Activations