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

    Neuronpedia

    INDEX
    Explanations

    phrases involving a specific time interval followed by an event or description

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that emphasize the word "Every."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Metatron
    -0.70
    dict
    -0.67
    zai
    -0.66
    ainment
    -0.64
    olas
    -0.64
    phabet
    -0.61
     Halls
    -0.58
     Osw
    -0.58
    hess
    -0.58
     Viz
    -0.57
    POSITIVE LOGITS
    THING
    1.48
    where
    1.22
     conceivable
    1.05
    body
    1.02
    things
    0.92
    WHERE
    0.88
    single
    0.88
    ursday
    0.84
     imaginable
    0.83
     single
    0.83
    Act Density 0.045%

    No Known Activations