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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Pearl Harbor"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "Pearl Harbor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.84
    enegger
    -0.81
    SPONSORED
    -0.76
    dit
    -0.73
    ellar
    -0.70
    arios
    -0.68
    hered
    -0.68
    ictions
    -0.67
    elsius
    -0.66
    PDATE
    -0.65
    POSITIVE LOGITS
     Harbor
    1.17
     Pearl
    1.01
    stein
    1.00
    ridge
    0.90
     Harbour
    0.89
    Pear
    0.86
    ãĥĥãĥī
    0.85
    sburg
    0.84
    fish
    0.79
     Flask
    0.75
    Act Density 0.019%

    No Known Activations