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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote specific time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActive
    -0.85
    alty
    -0.81
    alties
    -0.77
    ply
    -0.77
     sqor
    -0.75
    deck
    -0.75
    tical
    -0.72
    helle
    -0.70
    eus
    -0.68
    yss
    -0.67
    POSITIVE LOGITS
     downtime
    0.88
     periods
    0.87
     stagnation
    0.86
     uninterrupted
    0.83
     probation
    0.80
     hiatus
    0.78
     incarceration
    0.77
     silence
    0.76
     instability
    0.75
     delay
    0.75
    Act Density 0.077%

    No Known Activations