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

    Neuronpedia

    INDEX
    Explanations

    references to military facilities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blond
    -0.18
    stal
    -0.17
     vat
    -0.15
    IRT
    -0.15
    agn
    -0.15
     [][]
    -0.14
    vester
    -0.14
     Singer
    -0.14
    ertz
    -0.13
    ile
    -0.13
    POSITIVE LOGITS
     lys
    0.15
     grounds
    0.15
    usters
    0.15
    ummings
    0.14
    rray
    0.14
     Malk
    0.14
     serial
    0.14
    luk
    0.13
     Serial
    0.13
     Jak
    0.13
    Act Density 0.028%

    No Known Activations