INDEX
    Explanations

    punctuation and special characters

    New Auto-Interp
    Negative Logits
    amps
    -0.18
    chal
    -0.15
    variants
    -0.15
    latin
    -0.15
    iffe
    -0.14
     lut
    -0.13
    æĪ¶
    -0.13
    ined
    -0.13
    ait
    -0.13
    omic
    -0.13
    POSITIVE LOGITS
    ###↵↵
    0.17
    ###
    0.16
    ####
    0.15
    ##
    0.14
    ##_
    0.14
    #####
    0.14
     Karlov
    0.14
     Bek
    0.14
    clare
    0.14
    alink
    0.14
    Act Density 0.077%

    No Known Activations