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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structures related to code formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĥкÑĤ
    -0.20
    alog
    -0.16
    usercontent
    -0.16
     Wich
    -0.14
    ech
    -0.14
    uls
    -0.14
    EDIUM
    -0.14
    ÑĢави
    -0.14
     Exped
    -0.14
    /no
    -0.14
    POSITIVE LOGITS
    cq
    0.15
    arte
    0.15
    antes
    0.14
    olate
    0.14
    ãĥ¼ãĥĦ
    0.14
    ::__
    0.13
    idd
    0.13
    ante
    0.13
    osexual
    0.13
    ERRU
    0.13
    Act Density 0.002%

    No Known Activations