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

    Neuronpedia

    INDEX
    Explanations

    numeric values in the form of thousands

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Extras
    -0.69
    quickShipAvailable
    -0.67
     GEAR
    -0.59
    orously
    -0.58
    itionally
    -0.58
     Runes
    -0.58
    locks
    -0.56
     Lust
    -0.56
     Journals
    -0.56
     Parables
    -0.55
    POSITIVE LOGITS
     rating
    0.73
    ounce
    0.67
    hour
    0.65
    000
    0.64
    ottest
    0.63
    mile
    0.61
    issance
    0.59
    year
    0.59
    roller
    0.59
    797
    0.59
    Act Density 0.099%

    No Known Activations