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

    Neuronpedia

    INDEX
    Explanations

    names of countries, cities, or other geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of quantifiable metrics or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proport
    -0.72
     footing
    -0.72
    ¥ŀ
    -0.68
     undermin
    -0.67
     occas
    -0.65
     dazz
    -0.65
     Computing
    -0.64
     conclud
    -0.64
    abouts
    -0.64
     perspect
    -0.63
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.94
    rawdownloadcloneembedreportprint
    0.87
    ³³³³³³³³
    0.87
    ³³³³
    0.86
    Learn
    0.82
    However
    0.80
    Sym
    0.79
    Below
    0.79
    ³³³
    0.78
    Therefore
    0.78
    Act Density 0.432%

    No Known Activations