INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     couro
    0.48
    सायन
    0.43
    uesthouse
    0.41
     Lyman
    0.40
     pensée
    0.40
     archbishop
    0.39
    miers
    0.39
     freshen
    0.39
     travertine
    0.39
     sublattice
    0.39
    POSITIVE LOGITS
     README
    0.77
    README
    0.73
     GitHub
    0.69
     readme
    0.68
    readme
    0.66
     Github
    0.66
    github
    0.64
    GitHub
    0.64
    Readme
    0.63
     github
    0.57
    Act Density 0.007%

    No Known Activations