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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    person followed by who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我が家の
    -0.45
     Brew
    -0.44
    oa̍t
    -0.44
    olyb
    -0.43
     braking
    -0.43
     aegis
    -0.43
     Bidding
    -0.43
    bolic
    -0.43
     futile
    -0.42
    Viungo
    -0.42
    POSITIVE LOGITS
     person
    1.89
    person
    1.70
    Person
    1.69
     Person
    1.66
     PERSON
    1.48
     perſon
    1.37
     persons
    1.37
    PERSON
    1.36
     Persons
    1.28
    persons
    1.27
    Act Density 0.013%

    No Known Activations