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

    Neuronpedia

    INDEX
    Explanations

    references to a specific river or location named "Rivière"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oise
    -0.15
    quate
    -0.15
    undy
    -0.15
    ãĤ¢ãĥ¼
    -0.14
    pillar
    -0.14
    512
    -0.14
    927
    -0.14
    685
    -0.14
    iveness
    -0.14
    726
    -0.14
    POSITIVE LOGITS
    iera
    0.23
     riv
    0.23
    erview
    0.23
    eting
    0.20
    ieran
    0.18
    ière
    0.18
    alling
    0.17
    ETING
    0.16
    olt
    0.16
    ulet
    0.16
    Act Density 0.003%

    No Known Activations