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

    Neuronpedia

    INDEX
    Explanations

    long dashes or em dashes indicating breaks in thought or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.18
    iny
    -0.17
     latter
    -0.14
    ÙħاÙħ
    -0.14
    ãĤ
    -0.14
     opat
    -0.14
    esen
    -0.14
    inya
    -0.13
    ddd
    -0.13
    rap
    -0.13
    POSITIVE LOGITS
    ————————————————
    0.23
    ————————
    0.22
    ————
    0.18
    ãĤĪãģĨãģª
    0.16
    olicit
    0.15
    kest
    0.15
    ched
    0.14
    ноÑģÑĤ
    0.14
    ulla
    0.14
    recision
    0.14
    Act Density 0.076%

    No Known Activations