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

    Neuronpedia

    INDEX
    Explanations

    words related to morality and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsInitialized
    -0.50
    können
    -0.42
    setCancelable
    -0.40
    GTCX
    -0.40
    reactstrap
    -0.39
    égard
    -0.38
    StoryboardSegue
    -0.38
     Neglect
    -0.38
     mxArray
    -0.38
     useRouter
    -0.38
    POSITIVE LOGITS
    mor
    0.84
     moral
    0.84
     mor
    0.83
    MOR
    0.80
    moral
    0.77
     Morrison
    0.77
     morality
    0.77
    Morrison
    0.76
     Moral
    0.75
     MOR
    0.74
    Act Density 1.543%

    No Known Activations