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

    Neuronpedia

    INDEX
    Explanations

    concepts related to numerical limitations and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .viewer
    -0.17
    ãĤ¯ãĥĪ
    -0.15
    DMI
    -0.15
    'gc
    -0.14
    enne
    -0.14
    елÑĮно
    -0.14
    omnia
    -0.14
    ειο
    -0.14
    _TESTS
    -0.14
    æĺĮ
    -0.13
    POSITIVE LOGITS
    anel
    0.17
     fewer
    0.15
    osci
    0.15
    ìĭ¬
    0.15
     count
    0.15
     number
    0.14
    annels
    0.14
    imore
    0.14
    ismatic
    0.14
    å±Ģ
    0.14
    Act Density 0.375%

    No Known Activations