INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     slate
    -0.08
     Carl
    -0.07
     Spar
    -0.07
     cade
    -0.07
     crates
    -0.07
    $file
    -0.06
     Ja
    -0.06
    -plane
    -0.06
    .reg
    -0.06
     kabil
    -0.06
    POSITIVE LOGITS
     touch
    0.12
     Touch
    0.12
    Touch
    0.11
     touches
    0.09
    touch
    0.09
    -touch
    0.09
     TOUCH
    0.08
    _touch
    0.08
    (touch
    0.08
     touching
    0.07
    Act Density 0.011%

    No Known Activations