INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    json
    0.48
     json
    0.45
     JSON
    0.44
     pyridine
    0.42
    pyrid
    0.41
    Json
    0.40
    wParam
    0.40
     Snapchat
    0.39
    username
    0.39
     Json
    0.39
    POSITIVE LOGITS
     cow
    3.66
     cows
    3.48
    3.19
     Cows
    3.13
     Cow
    3.05
    Cow
    3.05
    cow
    2.94
     bovine
    2.81
    🐄
    2.75
    🐮
    2.75
    Act Density 0.039%

    No Known Activations