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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal roles, categories, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aurant
    -0.17
    ully
    -0.14
     aggress
    -0.14
    .reporting
    -0.14
    :CGRect
    -0.14
     May
    -0.14
     ../../../
    -0.14
    agini
    -0.13
     misdemean
    -0.13
    ór
    -0.13
    POSITIVE LOGITS
    841
    0.18
    \brief
    0.17
    gest
    0.16
    acman
    0.16
    errat
    0.15
    illard
    0.15
    olini
    0.15
    indh
    0.14
    IVEN
    0.14
    .called
    0.14
    Act Density 0.006%

    No Known Activations