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

    Neuronpedia

    INDEX
    Explanations

    time durations mentioned in minutes

    oai_token-act-pair · gpt-3.5-turbo

    time durations mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spons
    -0.80
    ebook
    -0.76
    bard
    -0.75
    rite
    -0.75
    rim
    -0.73
    ded
    -0.70
    liga
    -0.70
    ashtra
    -0.70
    myra
    -0.65
    uph
    -0.65
    POSITIVE LOGITS
     Minutes
    0.86
     livest
    0.86
     cooldown
    0.85
     ago
    0.85
    uters
    0.82
     elapsed
    0.81
     apiece
    0.80
     mins
    0.79
    neapolis
    0.79
     lapse
    0.77
    Act Density 0.044%

    No Known Activations