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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "days" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     SATURDAY
    -0.83
    SATURDAY
    -0.78
    Saturday
    -0.77
     SUNDAY
    -0.76
     Tolu
    -0.76
     Schmer
    -0.76
    abstractmethod
    -0.76
     Saturday
    -0.75
     scattata
    -0.75
     tomorrow
    -0.74
    POSITIVE LOGITS
     Days
    0.91
    Days
    0.76
     DAYS
    0.75
     days
    0.71
     dias
    0.69
    likes
    0.67
     Camino
    0.64
     way
    0.62
     jours
    0.62
    Evt
    0.61
    Act Density 0.028%

    No Known Activations