INDEX
    Explanations

    mentions of birds and bird-related activities

    New Auto-Interp
    Negative Logits
    ecer
    -0.18
    å·¡
    -0.16
    ayer
    -0.16
    ucch
    -0.16
    aurus
    -0.16
    stinence
    -0.15
     oran
    -0.15
    æ½ľ
    -0.15
    ewolf
    -0.15
    iske
    -0.15
    POSITIVE LOGITS
    song
    0.25
    sey
    0.24
     Bird
    0.20
    nest
    0.20
     bird
    0.19
     avi
    0.19
    Bird
    0.18
    -eye
    0.18
    ie
    0.18
    ong
    0.18
    Act Density 0.012%

    No Known Activations