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

    Neuronpedia

    INDEX
    Explanations

    references to morality and ethical dilemmas in human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzey
    -0.17
    wives
    -0.17
    outers
    -0.16
    RequiredMixin
    -0.14
    agnar
    -0.14
    essages
    -0.14
    вен
    -0.14
    èŃľ
    -0.14
    ả
    -0.14
    crop
    -0.14
    POSITIVE LOGITS
     person
    0.66
     individuals
    0.57
     persons
    0.56
     people
    0.54
    person
    0.44
     Person
    0.43
    _person
    0.43
    people
    0.41
     Individuals
    0.40
     personnes
    0.39
    Act Density 0.393%

    No Known Activations