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

    Neuronpedia

    INDEX
    Explanations

    references to weekends or days of the week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fact
    -0.66
    me
    -0.64
     way
    -0.62
    ner
    -0.62
     ce
    -0.61
     “
    -0.60
    küche
    -0.58
    pyx
    -0.58
    va
    -0.58
     va
    -0.58
    POSITIVE LOGITS
    Weekend
    1.43
     Weekend
    1.42
    weekend
    1.38
     weekend
    1.36
     weekends
    1.36
     WEEKEND
    1.25
    SUNDAY
    1.23
    SATURDAY
    1.21
     SUNDAY
    1.17
    Saturday
    1.15
    Act Density 0.074%

    No Known Activations