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

    Neuronpedia

    INDEX
    Explanations

    time intervals or frequencies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or repetition of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.68
    olas
    -0.64
     Journals
    -0.64
     Sakuya
    -0.62
     Jah
    -0.61
    ahime
    -0.60
    phabet
    -0.60
     Esports
    -0.59
     Carbuncle
    -0.58
     Grave
    -0.57
    POSITIVE LOGITS
    THING
    1.17
    where
    1.09
    single
    1.03
     year
    0.98
     month
    0.98
    day
    0.98
     imaginable
    0.98
     conceivable
    0.95
    WHERE
    0.93
     week
    0.92
    Act Density 0.037%

    No Known Activations