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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that indicate contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.17
    inand
    -0.16
    ichen
    -0.16
    chk
    -0.15
    ãĤ¤ãĤ¯
    -0.15
    ullo
    -0.15
    аÑĢам
    -0.14
    emme
    -0.14
    ìłķìĿĦ
    -0.14
    ombok
    -0.14
    POSITIVE LOGITS
    unn
    0.15
    umen
    0.15
     tamp
    0.15
     Nil
    0.15
     neutral
    0.15
    omm
    0.15
    Nam
    0.14
    课
    0.14
    alue
    0.14
    tat
    0.14
    Act Density 0.023%

    No Known Activations