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

    Neuronpedia

    INDEX
    Explanations

    references to religious figures and miraculous events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    866
    -0.15
    ุษ
    -0.14
     solitary
    -0.13
    Ｋ
    -0.13
    ä¸įå®ī
    -0.13
    .Euler
    -0.13
    .backup
    -0.13
    obre
    -0.13
    emento
    -0.13
    ardin
    -0.13
    POSITIVE LOGITS
     miracle
    0.63
     miracles
    0.61
    mir
    0.55
     Miracle
    0.53
     Mir
    0.50
     miraculous
    0.49
    Mir
    0.49
     wonders
    0.45
     mirac
    0.42
     wonder
    0.41
    Act Density 0.201%

    No Known Activations