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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    porno
    -0.14
    errupt
    -0.13
     Insecta
    -0.13
    erten
    -0.13
    _featured
    -0.13
    istrovstvÃŃ
    -0.12
    uffman
    -0.12
    aravel
    -0.12
    Ậ
    -0.12
    .ServiceModel
    -0.12
    POSITIVE LOGITS
     person
    1.10
     PERSON
    0.96
    person
    0.95
     Person
    0.95
    -person
    0.93
    Person
    0.87
     personal
    0.83
    PERSON
    0.83
     persons
    0.82
    .person
    0.81
    Act Density 0.472%

    No Known Activations