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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "them" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "them" indicating objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mire
    -0.65
     Omaha
    -0.62
    âĢ¢âĢ¢
    -0.62
     Lancaster
    -0.59
     LH
    -0.58
     Dian
    -0.57
    sic
    -0.56
    FIN
    -0.56
    ctor
    -0.56
     Lori
    -0.56
    POSITIVE LOGITS
    selves
    1.62
    atically
    1.58
     selves
    1.39
    atic
    1.27
    self
    1.05
     individually
    0.87
    ilitary
    0.86
    MpServer
    0.84
     themselves
    0.82
    atar
    0.82
    Act Density 0.106%

    No Known Activations