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

    Neuronpedia

    INDEX
    Explanations

    words related to architectural structures, specifically domes

    oai_token-act-pair · gpt-3.5-turbo

    references to domes and dome structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icia
    -0.75
    VD
    -0.71
    represented
    -0.71
    went
    -0.69
    orders
    -0.69
    ĩ
    -0.68
    avage
    -0.67
    ordered
    -0.67
    identified
    -0.66
    uggage
    -0.65
    POSITIVE LOGITS
     Dome
    0.93
     dome
    0.92
    buster
    0.78
    pole
    0.77
    busters
    0.76
    loo
    0.76
    ascus
    0.75
    ilion
    0.71
    ingen
    0.70
     retract
    0.67
    Act Density 0.005%

    No Known Activations