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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time or historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to past events or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.67
    ggle
    -0.66
    aspx
    -0.61
    ck
    -0.61
     pall
    -0.60
    okers
    -0.58
    minecraft
    -0.58
     Poles
    -0.58
    ittee
    -0.57
     haz
    -0.56
    POSITIVE LOGITS
    dated
    1.21
    packing
    0.92
    tracking
    0.85
    GROUND
    0.84
    fired
    0.83
    audi
    0.79
    packs
    0.78
    interstitial
    0.75
    actionDate
    0.75
    )=(
    0.74
    Act Density 0.025%

    No Known Activations