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

    Neuronpedia

    INDEX
    Explanations

    corporations or companies

    oai_token-act-pair · gpt-3.5-turbo

    references to corporations or corporate entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frie
    -0.74
     Emin
    -0.70
    hyde
    -0.69
    adow
    -0.69
    */(
    -0.68
    DonaldTrump
    -0.65
    schild
    -0.64
    âĶģ
    -0.64
    ¿½
    -0.63
    WARE
    -0.63
    POSITIVE LOGITS
    oreal
    1.17
    orporated
    0.97
    redibly
    0.94
    rador
    0.92
    ulent
    0.91
    amar
    0.87
    orp
    0.86
    ulence
    0.85
    identally
    0.83
    estial
    0.82
    Act Density 0.006%

    No Known Activations