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

    Neuronpedia

    INDEX
    Explanations

    structured proof elements in mathematical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elta
    -0.17
    oran
    -0.15
    ista
    -0.15
     Grim
    -0.14
    yps
    -0.14
    thon
    -0.14
    ateg
    -0.14
    ahr
    -0.14
    ort
    -0.13
    activation
    -0.13
    POSITIVE LOGITS
    ichern
    0.14
     neod
    0.14
    ?}",
    0.14
    COMPARE
    0.14
    compareTo
    0.13
    å®ı
    0.13
    .dw
    0.13
    tür
    0.13
    706
    0.13
    tility
    0.13
    Act Density 0.032%

    No Known Activations