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

    Neuronpedia

    INDEX
    Explanations

    pronouns 'them' and 'they' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular group or entity denoted by "them."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mire
    -0.64
     Dian
    -0.59
     Meier
    -0.59
     Lori
    -0.57
     Cao
    -0.56
     Megan
    -0.56
    Limit
    -0.55
     Lane
    -0.55
     Laurie
    -0.55
     Cabin
    -0.54
    POSITIVE LOGITS
    selves
    1.88
    atically
    1.76
     selves
    1.64
    atic
    1.55
    self
    1.36
     themselves
    0.95
    ovie
    0.92
    atics
    0.92
    ilitary
    0.92
     individually
    0.92
    Act Density 0.149%

    No Known Activations