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

    Neuronpedia

    INDEX
    Explanations

    references to the United States (U.S.)

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     STATS
    -0.76
    */(
    -0.73
    sticks
    -0.71
    ĵĺ
    -0.62
     ker
    -0.62
    bler
    -0.61
    arious
    -0.61
    SHIP
    -0.60
    milo
    -0.60
     PIT
    -0.60
    POSITIVE LOGITS
    ierra
    0.89
    eal
    0.86
    ADA
    0.85
    IDA
    0.84
    oday
    0.83
    eed
    0.79
    ESSION
    0.78
    igma
    0.78
    gt
    0.76
     Reloaded
    0.75
    Act Density 0.045%

    No Known Activations