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

    Neuronpedia

    INDEX
    Explanations

    mentions of something extraordinary or seemingly impossible happening

    oai_token-act-pair · gpt-3.5-turbo

    instances and variations of the word "miracle" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atana
    -0.82
    ivil
    -0.77
    irin
    -0.77
    iewicz
    -0.76
    ongyang
    -0.73
    isson
    -0.73
    onia
    -0.72
    RAFT
    -0.71
    ateur
    -0.70
    entric
    -0.70
    POSITIVE LOGITS
     miracle
    0.96
     miracles
    0.87
    ulously
    0.85
     absor
    0.84
     cures
    0.84
     healing
    0.83
     mirac
    0.83
     cure
    0.82
     Miracle
    0.81
     heal
    0.80
    Act Density 0.019%

    No Known Activations