INDEX
    Explanations

    sequences of repeated characters or symbols

    New Auto-Interp
    Negative Logits
     .”
    0.15
     .)
    0.19
     ."
    0.19
     .,
    0.20
     ‚
    0.21
     
    0.21
     
    0.21
     
    0.21
      
    0.22
     …”
    0.22
    POSITIVE LOGITS
    0.78
    󠀠
    0.77
    <unused0>
    0.76
     scolaires
    0.76
    0.75
     queſto
    0.75
    ſammen
    0.75
    0.75
    ParallelGroup
    0.75
    𨧀
    0.75
    Act Density 49.340%

    No Known Activations