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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" indicating significant moments or changes in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /pg
    -0.16
    antas
    -0.16
    erus
    -0.16
    ht
    -0.15
    lamaz
    -0.15
    ropolitan
    -0.14
    _graphics
    -0.14
    ä¾Ľ
    -0.14
    GRAPH
    -0.14
    ạo
    -0.14
    POSITIVE LOGITS
    aily
    0.15
    ãĤ«ãĥ¼
    0.15
    iesz
    0.15
    ãĤ·ãĥ¼
    0.15
     Bik
    0.15
     Elf
    0.15
    otions
    0.14
     desk
    0.14
    ality
    0.14
    wise
    0.14
    Act Density 0.033%

    No Known Activations