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

    Neuronpedia

    INDEX
    Explanations

    sections mentioning various news sources and reporters

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     charm
    -0.69
    rox
    -0.62
     rog
    -0.61
     Ally
    -0.58
    ounds
    -0.58
    hement
    -0.58
    agnetic
    -0.56
    uca
    -0.56
     precaution
    -0.55
    properties
    -0.55
    POSITIVE LOGITS
    ³³³³³³³³
    0.83
    rawdownloadcloneembedreportprint
    0.78
    ³³³
    0.77
    ³³³³³³³³³³³³³³³³
    0.76
     à¨
    0.70
     TED
    0.69
    BBC
    0.68
    NAS
    0.68
     Âł Âł
    0.68
    Bir
    0.68
    Act Density 0.207%

    No Known Activations