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

    Neuronpedia

    INDEX
    Explanations

    references to the White House and related governmental locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.84
    Expedia
    -0.66
    EDEFAULT
    -0.65
    elemField
    -0.64
    apimachinery
    -0.62
    memberof
    -0.61
    afterEach
    -0.60
    defineProperty
    -0.60
    bori
    -0.59
     ivelany
    -0.58
    POSITIVE LOGITS
     White
    1.74
    White
    1.38
     WHITE
    0.89
    WHITE
    0.75
    ホワイト
    0.65
     Castle
    0.65
     Putih
    0.62
     Rose
    0.61
     Biden
    0.58
     presidency
    0.58
    Act Density 0.143%

    No Known Activations