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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity and singular focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŀ
    -0.19
    zimmer
    -0.16
    IBC
    -0.16
    lok
    -0.16
    ARG
    -0.15
    bug
    -0.14
    abi
    -0.14
    aise
    -0.14
    ignon
    -0.13
    tte
    -0.13
    POSITIVE LOGITS
    emales
    0.18
    дÑı
    0.16
    azen
    0.16
    vern
    0.15
     seedu
    0.15
    emale
    0.14
    LayoutConstraint
    0.14
    imers
    0.14
    ATRIX
    0.14
    Decoration
    0.13
    Act Density 0.163%

    No Known Activations