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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or achievements within a timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IClient
    -0.16
    scribe
    -0.16
    radient
    -0.16
    otes
    -0.15
    Fuse
    -0.14
    ãĥĭãĥĥãĤ¯
    -0.14
    lian
    -0.14
    iram
    -0.14
    ùng
    -0.14
    aves
    -0.14
    POSITIVE LOGITS
    иÑģлов
    0.17
     Weiss
    0.16
    ìŀIJìĿ¸
    0.15
    addtogroup
    0.15
    ãĤ¤ãĥĦ
    0.14
    adora
    0.14
    warts
    0.13
    itz
    0.13
    ÑĤÑĢон
    0.13
    aira
    0.13
    Act Density 0.107%

    No Known Activations