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

    Neuronpedia

    INDEX
    Explanations

    references to political power dynamics and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UES
    -0.56
    opo
    -0.55
    romatic
    -0.54
    τισ
    -0.52
    ilanth
    -0.52
    блиоте
    -0.52
    Devil
    -0.51
    ייל
    -0.51
    '},
    -0.50
    '],
    -0.49
    POSITIVE LOGITS
     referenties
    0.84
    BASEPATH
    0.77
    AsUp
    0.73
    MergeFrom
    0.70
     estekak
    0.66
    reportWebVitals
    0.65
     propOrder
    0.63
    énario
    0.63
    MarshalTo
    0.62
    Билгалдахарш
    0.62
    Act Density 0.325%

    No Known Activations