Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to academic articles or research papers with substantial numeric identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    aarrggbb
    -1.05
    AsUp
    -0.93
     يتيمه
    -0.91
    ArrowToggle
    -0.85
    
    -0.85
    Autoritní
    -0.84
    RegressionTest
    -0.83
    IsMutable
    -0.80
    HtmlAttribute
    -0.79
    tanooga
    -0.76
    POSITIVE LOGITS
    TIL
    0.45
     βά
    0.45
     up
    0.44
     of
    0.43
    剥
    0.42
     after
    0.40
     bringing
    0.40
    芜
    0.39
     full
    0.38
     अप
    0.38
    Act Density 0.001%

    No Known Activations