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

    Neuronpedia

    INDEX
    Explanations

    references to miracles and miraculous events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oga
    -0.17
     saddle
    -0.16
    ounty
    -0.16
    ectar
    -0.16
    866
    -0.15
    ombat
    -0.14
    867
    -0.14
     fisse
    -0.14
    tridge
    -0.14
    SystemService
    -0.14
    POSITIVE LOGITS
     miracles
    0.31
     miracle
    0.30
     Miracle
    0.29
     miraculous
    0.26
    mir
    0.23
     záz
    0.22
     mirac
    0.21
    Mir
    0.20
     heal
    0.19
     Mir
    0.19
    Act Density 0.111%

    No Known Activations