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
    New Auto-Interp
    Negative Logits
    Portale
    -0.50
    Laurel
    -0.45
     Currie
    -0.45
     beira
    -0.44
    guang
    -0.43
    ″]
    -0.43
     Laurel
    -0.42
    Drainage
    -0.42
    لينكات
    -0.41
    Advisory
    -0.41
    POSITIVE LOGITS
     Person
    1.03
     person
    0.99
    Person
    0.96
     PERSON
    0.91
    person
    0.91
     Persons
    0.91
    Persons
    0.86
    persons
    0.85
     PERSONS
    0.85
     persons
    0.83
    Act Density 0.072%

    No Known Activations