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

    Neuronpedia

    INDEX
    Explanations

    references to weekends and related days

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Jays
    -0.73
    ely
    -0.73
    ley
    -0.66
    Datuak
    -0.65
     cylindrical
    -0.65
    ing
    -0.64
     fact
    -0.64
     rues
    -0.64
    Jays
    -0.64
    LEY
    -0.63
    POSITIVE LOGITS
     Weekend
    1.47
    Weekend
    1.41
     WEEKEND
    1.37
     weekends
    1.32
     weekend
    1.28
    weekend
    1.27
    SATURDAY
    1.02
     SATURDAY
    1.02
     Saturdays
    1.00
    ^(@)
    0.98
    Act Density 0.006%

    No Known Activations