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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NECT
    -0.15
    /logging
    -0.15
    izi
    -0.14
    sut
    -0.14
    浩
    -0.14
    endoza
    -0.13
    _CONVERT
    -0.13
    oulos
    -0.13
    imdi
    -0.13
    /boot
    -0.13
    POSITIVE LOGITS
     brav
    0.15
    oola
    0.14
    066
    0.14
    heimer
    0.14
    IGHL
    0.14
    arde
    0.14
    oeff
    0.13
    indre
    0.13
    ========↵
    0.13
    ube
    0.13
    Act Density 0.227%

    No Known Activations