INDEX
    Explanations

    punctuation

    New Auto-Interp
    Negative Logits
     baff
    -0.09
    Mir
    -0.09
     Mir
    -0.08
     mirrored
    -0.08
     stör
    -0.08
    ával
    -0.08
     Dona
    -0.08
     Spor
    -0.08
     impress
    -0.08
     Sociology
    -0.08
    POSITIVE LOGITS
     fetch
    0.08
     Fetch
    0.07
     khe
    0.07
    estin
    0.07
    -number
    0.07
    fetch
    0.07
     number
    0.07
    			 
    0.07
    _Object
    0.07
     ye
    0.07
    Act Density 0.504%

    No Known Activations