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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Jefferson"

    oai_token-act-pair · gpt-3.5-turbo

    references to Thomas Jefferson

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.79
    spring
    -0.78
    )=(
    -0.76
    product
    -0.72
    lator
    -0.72
    fare
    -0.72
    eq
    -0.72
    Terror
    -0.70
    comed
    -0.69
    atics
    -0.69
    POSITIVE LOGITS
     Jefferson
    1.24
     Parish
    1.01
     Davis
    0.92
    agne
    0.90
    sburg
    0.87
     Adams
    0.82
     Mills
    0.79
    izabeth
    0.76
     Dup
    0.75
     Wright
    0.75
    Act Density 0.008%

    No Known Activations