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

    Neuronpedia

    INDEX
    Explanations

    references to weekends and specific days of the week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kwan
    -0.71
     way
    -0.68
    かん
    -0.68
    Mew
    -0.66
    me
    -0.63
     προσ
    -0.63
    zulegen
    -0.61
     “
    -0.59
     Hines
    -0.59
     Matthews
    -0.58
    POSITIVE LOGITS
     saturday
    1.41
     Saturdays
    1.37
     Saturday
    1.36
    SATURDAY
    1.35
     SATURDAY
    1.34
    saturday
    1.31
     weekends
    1.31
     Weekend
    1.30
    Weekend
    1.29
    Saturday
    1.29
    Act Density 0.084%

    No Known Activations