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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal notations and buffer-related data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.22
    assa
    -0.15
     cort
    -0.15
    741
    -0.15
    ister
    -0.14
    ows
    -0.14
    soc
    -0.14
    ero
    -0.14
    lee
    -0.13
    739
    -0.13
    POSITIVE LOGITS
    @js
    0.14
    ãĥ¼ãĥĨ
    0.14
    osen
    0.14
    +:
    0.13
    unifu
    0.13
    edin
    0.13
     '{@
    0.13
    ÑĢок
    0.13
    RAY
    0.13
    åī£
    0.13
    Act Density 0.006%

    No Known Activations