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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical data or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egral
    -0.15
     FactoryBot
    -0.14
    iscard
    -0.14
    reesome
    -0.14
    ardon
    -0.13
    dings
    -0.13
    Æ¡i
    -0.13
    utation
    -0.13
    gressor
    -0.13
    [array
    -0.12
    POSITIVE LOGITS
     century
    0.91
     Century
    0.81
    cent
    0.73
    Century
    0.70
    -century
    0.68
     decade
    0.67
     Cent
    0.66
     centuries
    0.65
    ä¸ĸç´Ģ
    0.62
     cent
    0.61
    Act Density 0.273%

    No Known Activations