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

    Neuronpedia

    INDEX
    Explanations

    dates and timestamps

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas, in chronological data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uch
    -0.68
    eston
    -0.66
     domest
    -0.62
     antioxid
    -0.60
    ahu
    -0.60
    onite
    -0.59
    ĵĺ
    -0.59
    Maker
    -0.58
     cigars
    -0.58
     maize
    -0.58
    POSITIVE LOGITS
     partName
    0.91
    ramid
    0.83
    quickShipAvailable
    0.74
     PST
    0.73
     PDT
    0.72
     UTC
    0.71
     EDT
    0.70
     REUTERS
    0.68
    Reviewer
    0.67
    govtrack
    0.67
    Act Density 0.162%

    No Known Activations