INDEX
    Explanations

    the word "but" in various contexts

    New Auto-Interp
    Negative Logits
    ittest
    -0.15
    nip
    -0.15
    ikip
    -0.15
    å¡ļ
    -0.15
    pes
    -0.15
    anela
    -0.15
    βα
    -0.14
    optera
    -0.14
    essim
    -0.14
    792
    -0.13
    POSITIVE LOGITS
    chers
    0.17
    ts
    0.16
    OAD
    0.15
    ÑģÑıÑĤ
    0.15
    ape
    0.14
    rian
    0.14
     Jer
    0.14
    iker
    0.14
     Hass
    0.14
     Flo
    0.13
    Act Density 0.211%

    No Known Activations