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

    Neuronpedia

    INDEX
    Explanations

    references to strong and foundational elements, such as pillars and cornerstones

    oai_token-act-pair · gpt-3.5-turbo

    terms related to foundational concepts or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.82
    displayText
    -0.79
    ells
    -0.76
    ivil
    -0.72
    leneck
    -0.71
    sol
    -0.70
    ml
    -0.70
    lyss
    -0.69
    enegger
    -0.68
    TN
    -0.68
    POSITIVE LOGITS
     pillars
    1.04
     pillar
    0.98
     Pillar
    0.82
    hetical
    0.74
     fide
    0.74
    warts
    0.73
    ablishment
    0.71
    stones
    0.70
    OPLE
    0.68
    pillar
    0.67
    Act Density 0.025%

    No Known Activations