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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific location or time

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of timely occurrences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.75
    impl
    -0.67
    pora
    -0.66
    arching
    -0.62
    olor
    -0.61
    chwitz
    -0.58
    only
    -0.57
    alam
    -0.57
    dominated
    -0.57
    luster
    -0.56
    POSITIVE LOGITS
    cause
    0.76
     whiff
    0.67
     whisk
    0.67
    ifiable
    0.66
    ï¸
    0.64
     nick
    0.63
     luck
    0.63
    */(
    0.62
    æĦ
    0.62
    soDeliveryDate
    0.61
    Act Density 0.145%

    No Known Activations