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

    Neuronpedia

    INDEX
    Explanations

    mentions of time increments, specifically the word "minutes."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time durations, particularly minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.81
    keye
    -0.81
    bard
    -0.80
    spons
    -0.80
    ãĤ©
    -0.78
    ded
    -0.76
    keyes
    -0.69
    Las
    -0.68
    rim
    -0.68
    yrinth
    -0.67
    POSITIVE LOGITS
     livest
    0.86
    hift
    0.85
    isters
    0.83
     Minutes
    0.83
    otaur
    0.82
    uters
    0.82
     ticking
    0.79
    neapolis
    0.79
     cooldown
    0.77
     lapse
    0.75
    Act Density 0.030%

    No Known Activations