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

    Neuronpedia

    INDEX
    Explanations

    words related to memorabilia and memory

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and memorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.73
    IRO
    -0.70
     Silk
    -0.67
     Empires
    -0.63
    WP
    -0.62
     Syrians
    -0.61
     Citizens
    -0.61
     ACS
    -0.60
    Conclusion
    -0.60
    Merit
    -0.60
    POSITIVE LOGITS
    abilia
    1.60
     memor
    1.32
    ably
    1.03
    ographed
    0.98
    etically
    0.95
    ific
    0.95
    ruction
    0.91
    andum
    0.87
    brance
    0.87
    istically
    0.87
    Act Density 0.008%

    No Known Activations