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

    Neuronpedia

    INDEX
    Explanations

    questions in the format "Is it...?" with a focus on various topics

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or statements that start with "Is it" relating to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.68
    rals
    -0.67
    icates
    -0.67
    terness
    -0.65
    english
    -0.64
    rates
    -0.63
    ges
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
    gers
    -0.59
    itud
    -0.58
    POSITIVE LOGITS
     hypocr
    0.77
    ourke
    0.68
    ffield
    0.65
    iasis
    0.62
    ?",
    0.62
    zzo
    0.61
     tha
    0.59
     exception
    0.59
    tha
    0.58
    isi
    0.58
    Act Density 0.294%

    No Known Activations