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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /DD
    -0.17
     DISCLAIM
    -0.15
     shalt
    -0.15
    ekce
    -0.14
    borough
    -0.14
    bersome
    -0.14
    itan
    -0.14
    bor
    -0.14
    (factor
    -0.14
     "";č↵
    -0.14
    POSITIVE LOGITS
    ussen
    0.17
     Judiciary
    0.15
    ivery
    0.14
    /or
    0.14
     non
    0.14
    unate
    0.14
    457
    0.14
    بت
    0.14
    rogen
    0.14
    olan
    0.13
    Act Density 0.122%

    No Known Activations