INDEX
    Explanations

    technical writing

    This neuron activates on sentence-initial discourse markers and transitional phrases (e.g. “In view of,” “According to,” “Among,” etc.).

    New Auto-Interp
    Negative Logits
    -0.07
    Visited
    -0.06
    Processed
    -0.06
     distur
    -0.06
    books
    -0.06
    аті
    -0.06
    .Hidden
    -0.06
    Average
    -0.06
    Hy
    -0.06
    .Weight
    -0.06
    POSITIVE LOGITS
     przez
    0.07
    umin
    0.06
    /team
    0.06
     olacağ
    0.06
    .cuda
    0.06
     ApplicationUser
    0.06
     इन
    0.06
     sefer
    0.06
    "]:↵
    0.06
    iswa
    0.06
    Act Density 0.027%

    No Known Activations