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

    Neuronpedia

    INDEX
    Explanations

    references to actions or characteristics related to a specific group of people

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "they" indicating a focus on people or groups being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eleven
    -0.89
    CCC
    -0.85
     Glob
    -0.72
     Tad
    -0.70
     Kinn
    -0.70
    UTC
    -0.67
     Globe
    -0.67
     Atlantis
    -0.66
     Cable
    -0.66
     Flan
    -0.66
    POSITIVE LOGITS
    're
    1.28
    've
    1.03
    selves
    1.02
    'll
    0.99
    self
    0.91
     selves
    0.89
     themselves
    0.89
     own
    0.87
     perceive
    0.85
     deserve
    0.85
    Act Density 0.229%

    No Known Activations