INDEX
    Explanations

    the pronoun "It" in various contexts

    New Auto-Interp
    Negative Logits
    noc
    -0.17
    ember
    -0.16
     Trails
    -0.16
     trails
    -0.15
    phia
    -0.15
     stuff
    -0.15
     str
    -0.15
    iaÅĤa
    -0.15
    lore
    -0.15
    ergus
    -0.14
    POSITIVE LOGITS
    ador
    0.17
    oret
    0.15
    odore
    0.15
    odor
    0.15
    èĥ
    0.15
    une
    0.14
    ulus
    0.14
     Es
    0.14
    _Lean
    0.13
    retim
    0.13
    Act Density 0.211%

    No Known Activations