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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, specifically related to durations of months, years, or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.69
    Son
    -0.68
    ucci
    -0.66
    Tro
    -0.66
     Packs
    -0.65
    coming
    -0.65
    STAR
    -0.65
    do
    -0.63
    se
    -0.63
    UTF
    -0.62
    POSITIVE LOGITS
     compr
    0.82
     elapsed
    0.78
     devoted
    0.76
    ients
    0.74
    ELF
    0.71
    EStreamFrame
    0.67
     adjourn
    0.67
     reckoning
    0.65
     captivity
    0.65
    dayName
    0.64
    Act Density 0.140%

    No Known Activations