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

    Neuronpedia

    INDEX
    Explanations

    time durations denoted in minutes

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time in minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bard
    -0.82
    spons
    -0.77
    ashtra
    -0.75
    ded
    -0.71
    ebook
    -0.69
    liga
    -0.69
    imaru
    -0.68
    rim
    -0.68
    Las
    -0.67
    keye
    -0.67
    POSITIVE LOGITS
     cooldown
    0.85
     elapsed
    0.85
     Minutes
    0.84
    hift
    0.84
     lapse
    0.84
     livest
    0.84
     ago
    0.81
    uters
    0.80
     ticking
    0.76
    otaur
    0.75
    Act Density 0.034%

    No Known Activations