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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.70
    !/
    -0.67
    é»Ĵ
    -0.62
     veins
    -0.62
     leaps
    -0.61
     arose
    -0.60
     stems
    -0.59
    ahime
    -0.58
     necessity
    -0.57
     stemmed
    -0.56
    POSITIVE LOGITS
     pione
    0.71
    ĸļ士
    0.62
    senal
    0.60
    vantage
    0.60
    ò
    0.60
    ā
    0.59
     earthqu
    0.59
    ú
    0.59
    ø
    0.58
    č
    0.58
    Act Density 0.546%

    No Known Activations