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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional states or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '},
    -0.93
    )");
    -0.88
    )*/
    -0.82
    "",
    -0.81
    $")
    -0.81
    }*/
    -0.80
    それとも
    -0.79
    []
    -0.79
     
    -0.78
    =*/
    -0.78
    POSITIVE LOGITS
    .
    0.79
    !
    0.62
    !!!
    0.58
    oporosis
    0.58
    !!
    0.57
    外部链接
    0.56
    loroethane
    0.56
     ожи
    0.55
     plagioclase
    0.55
    ↵↵↵
    0.54
    Act Density 0.076%

    No Known Activations