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

    Neuronpedia

    INDEX
    Explanations

    names of people, places, and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    using
    -0.15
    odore
    -0.15
    ughters
    -0.15
    irt
    -0.15
    quot
    -0.15
    /order
    -0.15
     обÑĢазом
    -0.15
    quez
    -0.14
    xed
    -0.14
    dÃŃ
    -0.14
    POSITIVE LOGITS
    alley
    0.18
    idental
    0.18
     behalf
    0.18
    yssey
    0.17
    chest
    0.15
    verture
    0.15
    Å¡etÅĻ
    0.15
    ubre
    0.15
    ancock
    0.15
    -fashioned
    0.15
    Act Density 0.497%

    No Known Activations