INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    insky
    -0.08
    Mono
    -0.08
    ungeon
    -0.07
    (ins
    -0.07
     dumb
    -0.07
    oni
    -0.07
    Filters
    -0.07
    _Line
    -0.07
    Spaces
    -0.06
     hmm
    -0.06
    POSITIVE LOGITS
    RCT
    0.08
    0.07
    CT
    0.07
     ц
    0.07
    чает
    0.06
    ิญ
    0.06
     achie
    0.06
    ecz
    0.06
    )}"↵
    0.06
     ICT
    0.06
    Act Density 0.001%

    No Known Activations