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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with scientific investigation and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.67
     scolaires
    -0.62
     religieuses
    -0.61
     chré
    -0.58
     geweest
    -0.58
     domestiques
    -0.54
     spindles
    -0.54
     विश्वसनीयता
    -0.53
    ++.
    -0.53
     Ause
    -0.52
    POSITIVE LOGITS
    리는
    0.69
    apimachinery
    0.68
    UnusedPrivate
    0.67
    들은
    0.64
    이는
    0.60
    balleur
    0.60
     is
    0.58
     είναι
    0.58
     would
    0.58
     betweenstory
    0.58
    Act Density 2.347%

    No Known Activations