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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "all."

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity or universality in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.67
     ASAP
    -0.61
    mire
    -0.59
     Loading
    -0.58
    aria
    -0.58
     Hold
    -0.58
    poke
    -0.57
    andra
    -0.57
    raped
    -0.57
    well
    -0.56
    POSITIVE LOGITS
     imaginable
    0.85
    士
    0.75
     tabl
    0.73
     conceivable
    0.71
    hyde
    0.69
    Downloadha
    0.64
    intestinal
    0.64
     aspirin
    0.63
     Occupations
    0.63
    chens
    0.62
    Act Density 0.059%

    No Known Activations