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

    Neuronpedia

    INDEX
    Explanations

    keywords related to discussing or talking about various topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning discussions or topics that people engage in

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.71
    sky
    -0.68
    Released
    -0.68
    waters
    -0.66
    Added
    -0.65
    Written
    -0.65
    gallery
    -0.63
    ©¶æ¥µ
    -0.62
    à¥
    -0.62
    assi
    -0.62
    POSITIVE LOGITS
     reforming
    0.81
    eday
    0.76
     how
    0.73
     topics
    0.73
     specifics
    0.69
    pheus
    0.68
     behalf
    0.67
     stopping
    0.65
     whether
    0.65
     quitting
    0.65
    Act Density 0.075%

    No Known Activations