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

    Neuronpedia

    INDEX
    Explanations

    phrases related to frequency or time intervals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "every" in relation to time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phabet
    -0.70
    olas
    -0.66
    ahime
    -0.62
     Esports
    -0.61
     Sakuya
    -0.60
     Jah
    -0.59
    hess
    -0.58
     Quinn
    -0.57
     Osw
    -0.57
     Journals
    -0.57
    POSITIVE LOGITS
    THING
    1.18
    where
    1.09
    single
    0.97
    things
    0.95
     conceivable
    0.92
     single
    0.92
    ħĭ
    0.92
    Ĥª
    0.89
     imaginable
    0.88
     inch
    0.88
    Act Density 0.040%

    No Known Activations