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

    Neuronpedia

    INDEX
    Explanations

    religious buildings or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to cathedrals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terness
    -0.91
    ilit
    -0.90
    bling
    -0.87
    union
    -0.83
    graph
    -0.83
    bles
    -0.82
    fits
    -0.81
    laus
    -0.80
    bell
    -0.80
    owship
    -0.80
    POSITIVE LOGITS
     Cathedral
    0.89
     Capitals
    0.70
     tabl
    0.68
     Clause
    0.67
     nursery
    0.66
     Hels
    0.66
     Divinity
    0.66
     Dawkins
    0.65
     envelope
    0.64
     PRESS
    0.63
    Act Density 0.058%

    No Known Activations