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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "person" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BagLayout
    -0.86
    ()]
    -0.81
    gemar
    -0.80
     <<=
    -0.79
    >\<^
    -0.79
    "]);
    -0.79
    ientôt
    -0.78
    łgorzata
    -0.77
    ReadAll
    -0.77
     **/
    -0.77
    POSITIVE LOGITS
     Person
    1.98
     person
    1.92
     PERSON
    1.83
     Persons
    1.83
    person
    1.83
    Person
    1.80
    PERSON
    1.68
    Persons
    1.68
     persons
    1.66
     PERSONS
    1.62
    Act Density 0.035%

    No Known Activations