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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant event or change

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mates
    -0.70
     Dragonbound
    -0.66
    quickShipAvailable
    -0.66
     ç¥ŀ
    -0.65
     Gleaming
    -0.63
     Tycoon
    -0.63
    igion
    -0.62
     Dek
    -0.62
     Monsters
    -0.61
     peers
    -0.61
    POSITIVE LOGITS
    ŃĶ
    1.05
    ģ«
    0.98
     underway
    0.79
    ritten
    0.76
    berra
    0.73
    needed
    0.72
    ģ
    0.72
    ļé
    0.71
     arisen
    0.71
    »Ĵ
    0.71
    Act Density 0.454%

    No Known Activations