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

    Neuronpedia

    INDEX
    Explanations

    dates, years, and specific numerical values mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andem
    -0.67
    ress
    -0.64
    osures
    -0.62
    ocaust
    -0.61
    ega
    -0.61
    urai
    -0.60
    aukee
    -0.59
    stead
    -0.59
    cosystem
    -0.57
    orf
    -0.56
    POSITIVE LOGITS
     they
    0.91
    soever
    0.83
     although
    0.75
     fateful
    0.74
     "[
    0.71
    eday
    0.70
     '[
    0.69
     we
    0.69
     there
    0.67
     he
    0.67
    Act Density 0.272%

    No Known Activations