INDEX
    Explanations

    opening curly braces in code

    New Auto-Interp
    Negative Logits
    transQ
    -0.84
    httphttps
    -0.81
    rungsseite
    -0.81
    تقاوى
    -0.78
     ſind
    -0.77
     GoogleFonts
    -0.77
     ſch
    -0.76
    ſcher
    -0.75
    WriteTagHelper
    -0.74
    iſen
    -0.74
    POSITIVE LOGITS
    {
    0.56
    :
    0.46
    a
    0.38
     a
    0.36
    ida
    0.35
    ia
    0.35
    ic
    0.35
    ire
    0.35
    {
    
    0.35
    ":
    0.35
    Act Density 0.060%

    No Known Activations