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

    Neuronpedia

    INDEX
    Explanations

    references to miraculous events or things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to miracles or extraordinary occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateur
    -0.86
    remlin
    -0.80
    resp
    -0.79
    ivil
    -0.79
    published
    -0.78
    uggish
    -0.77
    agle
    -0.76
    oln
    -0.75
    atana
    -0.75
    ateurs
    -0.73
    POSITIVE LOGITS
     miracle
    1.39
     miracles
    1.13
     Miracle
    1.09
     miraculous
    0.95
     heal
    0.93
     cures
    0.93
    ulously
    0.92
     mirac
    0.90
     cure
    0.88
     absor
    0.87
    Act Density 0.010%

    No Known Activations