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

    Neuronpedia

    INDEX
    Explanations

    pronouns 'them' or 'they' specifically

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CCC
    -0.65
    mire
    -0.62
     KC
    -0.61
    JD
    -0.59
     Salon
    -0.58
    KC
    -0.57
     Prototype
    -0.57
    cock
    -0.57
     House
    -0.56
     POLITICO
    -0.56
    POSITIVE LOGITS
    selves
    1.86
     selves
    1.58
    atically
    1.49
    atic
    1.31
    self
    1.29
    ovie
    0.87
    atics
    0.86
     individually
    0.85
     themselves
    0.83
    're
    0.80
    Act Density 0.132%

    No Known Activations