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

    Neuronpedia

    INDEX
    Explanations

    references to extraordinary events or happenings often described as 'miracles'

    oai_token-act-pair · gpt-3.5-turbo

    references to miracles or miraculous events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iewicz
    -0.79
    choes
    -0.75
    atana
    -0.75
    ivil
    -0.75
    irin
    -0.74
    ongyang
    -0.73
    ensor
    -0.72
    ictionary
    -0.71
    avid
    -0.71
    competitive
    -0.70
    POSITIVE LOGITS
     miracle
    0.98
     Miracle
    0.93
     miracles
    0.90
    ulously
    0.89
     cures
    0.89
     healing
    0.87
     cure
    0.85
     heal
    0.84
     mirac
    0.83
     absor
    0.77
    Act Density 0.031%

    No Known Activations