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

    Neuronpedia

    INDEX
    Explanations

    phrases used as guiding principles or mottos

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to guiding principles or beliefs, such as mantras and mottos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wolves
    -0.77
    NetMessage
    -0.77
    Wil
    -0.74
    ships
    -0.73
    */(
    -0.72
    lations
    -0.70
    pedia
    -0.70
    orthy
    -0.70
    uggage
    -0.69
    asser
    -0.69
    POSITIVE LOGITS
     mantra
    1.24
     motto
    1.18
     mant
    0.94
    rix
    0.76
     precept
    0.73
     guiding
    0.73
     chant
    0.70
     guru
    0.70
     theme
    0.68
    tta
    0.66
    Act Density 0.019%

    No Known Activations