INDEX
    Explanations

    Getting rid or giving

    New Auto-Interp
    Negative Logits
     had
    -1.09
    had
    -0.92
     gave
    -0.82
    Had
    -0.81
     Had
    -0.70
     hadde
    -0.68
     avevano
    -0.66
     hatte
    -0.65
     aveva
    -0.63
     hatten
    -0.60
    POSITIVE LOGITS
    ]='\
    0.93
     Monfieur
    0.82
     myſelf
    0.77
     Efq
    0.76
     Majefty
    0.72
     ProtoMessage
    0.70
    0.69
     risen
    0.69
     purpoſe
    0.68
    $$
    
    0.68
    Act Density 1.270%

    No Known Activations