INDEX
    Explanations

    references to children's literature, particularly middle-grade novels

    New Auto-Interp
    Negative Logits
    aise
    -0.16
     Sty
    -0.15
    lect
    -0.15
    infeld
    -0.15
    *)((
    -0.15
    AndView
    -0.14
    USIC
    -0.14
    PCP
    -0.14
    ugu
    -0.13
    IFT
    -0.13
    POSITIVE LOGITS
     picture
    0.34
    picture
    0.30
     Picture
    0.28
    -picture
    0.26
    Picture
    0.25
     middle
    0.23
    .picture
    0.23
    -middle
    0.23
    _picture
    0.23
    middle
    0.21
    Act Density 0.171%

    No Known Activations