INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     motorway
    -0.09
     foo
    -0.08
     triple
    -0.08
    Trip
    -0.08
     quadru
    -0.08
     meltdown
    -0.08
     lemma
    -0.07
    Slash
    -0.07
    uisse
    -0.07
    -0.07
    POSITIVE LOGITS
    <|endoftext|>
    0.10
    _pose
    0.09
    _{\
    0.08
    .erp
    0.08
    _shape
    0.08
    .GUI
    0.08
    āc
    0.08
    0.08
    0.08
     mediante
    0.08
    Act Density 0.078%

    No Known Activations