INDEX
    Explanations

    punctuation and special characters within the text

    New Auto-Interp
    Negative Logits
    oyal
    -0.15
     Baron
    -0.15
    ules
    -0.14
    ites
    -0.14
     Barcl
    -0.14
    owy
    -0.14
    954
    -0.13
    ะ
    -0.13
    isk
    -0.13
     barriers
    -0.13
    POSITIVE LOGITS
     Foot
    0.24
     foot
    0.19
     FOOT
    0.18
    Foot
    0.17
    foot
    0.16
    åĢī
    0.15
     çģ
    0.15
    leneck
    0.15
    館
    0.14
     footprint
    0.14
    Act Density 0.028%

    No Known Activations