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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to dates or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .struts
    -0.19
    atever
    -0.16
    stal
    -0.15
    agra
    -0.15
     loose
    -0.15
    á»ĭ
    -0.15
    lder
    -0.14
    ajs
    -0.14
    uple
    -0.14
     lead
    -0.14
    POSITIVE LOGITS
     âĹĦ
    0.15
    uess
    0.14
    å¿Ĺ
    0.14
    EXPECTED
    0.14
    kie
    0.14
    peater
    0.14
    ìĤ¬íķŃ
    0.14
     ÐŀлекÑģанд
    0.13
    ÃĵN
    0.13
    gle
    0.13
    Act Density 0.073%

    No Known Activations