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

    Neuronpedia

    INDEX
    Explanations

    short durations of time

    oai_token-act-pair · gpt-3.5-turbo

    references to time duration in seconds and minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iHUD
    -0.74
    annis
    -0.67
    irie
    -0.65
    lict
    -0.63
    gging
    -0.62
    ventions
    -0.62
    gat
    -0.61
    yer
    -0.61
    spons
    -0.61
    angered
    -0.61
    POSITIVE LOGITS
     elapsed
    1.32
     intervals
    0.94
     ago
    0.87
     increments
    0.85
    seconds
    0.81
    aneously
    0.81
    ngth
    0.81
     timer
    0.77
     interval
    0.76
     cooldown
    0.75
    Act Density 0.033%

    No Known Activations