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

    Neuronpedia

    INDEX
    Explanations

    references to points or key ideas in arguments or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usted
    -0.17
    gow
    -0.17
    itational
    -0.16
    ±Ð¾ÑĤ
    -0.15
    urette
    -0.15
    aeper
    -0.14
    ilitating
    -0.14
    ipi
    -0.14
    æ±Ĺ
    -0.14
    ellen
    -0.14
    POSITIVE LOGITS
    point
    0.19
    points
    0.18
    åĦ¿
    0.18
    -point
    0.17
    sto
    0.16
    ãĥ
    0.16
     зÑĢениÑı
    0.16
    gerald
    0.16
    aneous
    0.15
    nie
    0.15
    Act Density 0.092%

    No Known Activations