INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ugly
    0.68
    weird
    0.68
     stupid
    0.63
     idiots
    0.63
     stupidity
    0.63
     nasty
    0.61
     idiot
    0.61
     Stupid
    0.61
     pitiful
    0.60
    ugly
    0.60
    POSITIVE LOGITS
     unwell
    0.46
    Spectrum
    0.45
     understandably
    0.45
    TikTok
    0.45
     incarcerated
    0.44
    alleng
    0.42
     incredible
    0.42
    *}$
    0.41
     VLC
    0.41
     respectfully
    0.41
    Act Density 0.109%

    No Known Activations