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

    Neuronpedia

    INDEX
    Explanations

    time-related words and phrases, particularly durations such as minutes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific durations of time in minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.73
    ports
    -0.68
    liga
    -0.67
    ourge
    -0.65
     dice
    -0.64
    ifted
    -0.64
    acea
    -0.63
    etr
    -0.63
     Commodore
    -0.63
    hiro
    -0.62
    POSITIVE LOGITS
    endment
    1.01
    minute
    0.83
    aneously
    0.82
    istance
    0.80
    quart
    0.77
    summary
    0.75
    fps
    0.74
    motion
    0.74
    strument
    0.72
    theless
    0.72
    Act Density 0.010%

    No Known Activations