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

    Neuronpedia

    INDEX
    Explanations

    references to specific television shows and significant societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olulu
    -0.62
     Invention
    -0.61
    Marginal
    -0.56
    !.
    -0.56
    };
    -0.52
    rawdownloadcloneembedreportprint
    -0.52
    pedia
    -0.51
    idav
    -0.49
    cellaneous
    -0.49
    SourceFile
    -0.49
    POSITIVE LOGITS
     should
    0.91
     could
    0.89
     cannot
    0.84
     exists
    0.83
     hadn
    0.83
     might
    0.83
     existed
    0.82
     would
    0.81
     lacked
    0.80
     had
    0.79
    Act Density 0.573%

    No Known Activations