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

    Neuronpedia

    INDEX
    Explanations

    mentions of ancient civilizations or artifacts

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient entities, cultures, or artifacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annel
    -0.73
    Spot
    -0.70
     Handling
    -0.69
     CPS
    -0.68
    cade
    -0.66
    fox
    -0.65
    respond
    -0.65
    haw
    -0.64
     Truck
    -0.64
     Duff
    -0.63
    POSITIVE LOGITS
     ancient
    3.26
    Ancient
    2.44
     Ancient
    2.39
     antiquity
    2.13
    cients
    2.01
     prehistoric
    1.85
     ancestral
    1.72
     medieval
    1.65
     archaic
    1.58
     antique
    1.57
    Act Density 0.020%

    No Known Activations