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

    Neuronpedia

    INDEX
    Explanations

    words related to borrowing and neighborhoods

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "borrowing" or related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HER
    -0.95
    uality
    -0.74
    apo
    -0.67
    agate
    -0.65
    aminer
    -0.64
    urer
    -0.62
    ery
    -0.62
     Dragonbound
    -0.62
    Performance
    -0.62
    mble
    -0.61
    POSITIVE LOGITS
    bor
    1.18
    rowing
    0.97
    rower
    0.91
    icultural
    0.85
    ror
    0.80
    poon
    0.79
    sten
    0.78
    fusc
    0.78
    oreal
    0.77
    iculture
    0.75
    Act Density 0.004%

    No Known Activations