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

    Neuronpedia

    INDEX
    Explanations

    mentions of elevators or elevator shafts

    oai_token-act-pair · gpt-3.5-turbo

    references to elevators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.83
    nesses
    -0.81
    lust
    -0.80
    ned
    -0.75
    ness
    -0.74
    arah
    -0.72
    words
    -0.71
    nar
    -0.70
    nia
    -0.69
    wcsstore
    -0.68
    POSITIVE LOGITS
     shaft
    1.10
    inson
    0.94
     elevator
    0.93
     doors
    0.84
     elev
    0.83
     entrances
    0.83
     pitch
    0.82
     stairs
    0.78
    ysis
    0.77
    idge
    0.76
    Act Density 0.025%

    No Known Activations