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

    Neuronpedia

    INDEX
    Explanations

    words related to significant buildings or structures, especially Gothic cathedrals

    oai_token-act-pair · gpt-3.5-turbo

    references to cathedrals and significant religious buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imester
    -0.67
    ãĥĥãĥī
    -0.65
    à©
    -0.64
    Downloadha
    -0.64
    @#&
    -0.61
    yon
    -0.61
    wrong
    -0.60
    ãģĹ
    -0.60
    ealous
    -0.59
    EStream
    -0.58
    POSITIVE LOGITS
     tower
    0.98
     perched
    0.96
     towers
    0.95
     annex
    0.92
    tower
    0.90
     occupancy
    0.82
     Towers
    0.81
     flanked
    0.81
     occupies
    0.80
     Located
    0.79
    Act Density 0.289%

    No Known Activations