INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Fam
    -0.09
     fanc
    -0.08
     Fam
    -0.08
     halluc
    -0.08
     reconn
    -0.08
     shitty
    -0.08
     fam
    -0.08
    fam
    -0.08
     Fuck
    -0.08
     laut
    -0.07
    POSITIVE LOGITS
    Consulta
    0.09
    jeve
    0.08
     Heads
    0.08
    0.08
    ostra
    0.07
    516
    0.07
    �↵↵
    0.07
     Examination
    0.07
    Ln
    0.07
    Totals
    0.07
    Act Density 0.592%

    No Known Activations