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

    Neuronpedia

    INDEX
    Explanations

    references to waste or trash, particularly in the context of the term "litter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornment
    -0.15
    828
    -0.15
    ext
    -0.15
    itat
    -0.15
     (
    -0.14
     ich
    -0.14
    ritte
    -0.14
    ÏĦηÏĥη
    -0.14
    rtl
    -0.14
    vol
    -0.14
    POSITIVE LOGITS
    adel
    0.17
    ãĥ¼ãĥĬ
    0.15
    ãĥ¼ãĤ¿
    0.15
    tp
    0.14
    ãĥ¼ãĥĭ
    0.14
     ê±
    0.14
    ausal
    0.14
    iag
    0.14
    raquo
    0.14
    umsuz
    0.14
    Act Density 0.005%

    No Known Activations