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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to miracles and astonishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.60
    gitte
    -0.55
     necessariamente
    -0.54
    nteral
    -0.54
    invalidate
    -0.53
    rifugal
    -0.50
    どうしても
    -0.50
     Glieder
    -0.49
    copyWith
    -0.47
    衛門
    -0.47
    POSITIVE LOGITS
     miracle
    1.82
     miracles
    1.80
     wonders
    1.66
     miraculous
    1.63
     Miracle
    1.58
     marvels
    1.57
    miracle
    1.55
     wonder
    1.54
    wonder
    1.52
     WONDER
    1.49
    Act Density 0.141%

    No Known Activations