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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and election-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hyatt
    -0.66
    клопе
    -0.65
    zter
    -0.65
     numberWith
    -0.62
    s
    -0.62
     Rink
    -0.61
    Modes
    -0.61
     Jong
    -0.61
     Dominicana
    -0.60
     Hib
    -0.60
    POSITIVE LOGITS
     Buhari
    1.17
     صوتيه
    0.98
    Buhari
    0.94
    ########.
    0.93
    eradish
    0.92
     chakras
    0.88
     Avalanche
    0.86
     Waller
    0.83
    رشف
    0.81
    XmlAccessorType
    0.81
    Act Density 0.030%

    No Known Activations