INDEX
    Explanations

    phrases indicating similarity or comparison

    New Auto-Interp
    Negative Logits
    "):
    
    -0.73
     Theſe
    -0.70
    ArrowToggle
    -0.70
    ']):
    -0.67
    ":
    
    -0.67
    Autoritní
    -0.65
    onViewCreated
    -0.63
    "]);
    
    -0.63
     PEP
    -0.62
    lesssim
    -0.60
    POSITIVE LOGITS
     Neub
    0.55
    qrstuvwxyz
    0.51
     kereszt
    0.49
    stagland
    0.49
    getitem
    0.48
     للمعارف
    0.48
     kív
    0.47
     "'");
    0.47
    cherichia
    0.47
     tölt
    0.47
    Act Density 0.118%

    No Known Activations