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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data, statistics, and information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ories" or its variations, indicating a focus on narratives or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rella
    -0.66
    zee
    -0.62
    xon
    -0.61
     TSA
    -0.59
    Rot
    -0.59
    00200000
    -0.58
    class
    -0.58
     SP
    -0.58
    ĺħ
    -0.56
    Topics
    -0.56
    POSITIVE LOGITS
    ories
    1.53
    ynthesis
    1.01
    poons
    0.99
    terness
    0.93
    ORY
    0.89
    orie
    0.87
    pring
    0.86
    anguage
    0.82
    ynt
    0.81
    uggest
    0.79
    Act Density 0.004%

    No Known Activations