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

    Neuronpedia

    INDEX
    Explanations

    references to magic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ExecuteReader
    -0.57
     Constitution
    -0.49
    fromCharCode
    -0.49
    Зноскі
    -0.49
     longitude
    -0.49
     kPa
    -0.48
     GEOLOGY
    -0.47
     inse
    -0.47
     fitness
    -0.47
     smtplib
    -0.47
    POSITIVE LOGITS
    Magic
    0.62
     Magic
    0.62
     magic
    0.60
    magic
    0.59
    Hybrid
    0.57
    MAGIC
    0.56
     measured
    0.56
    measured
    0.55
     Hybrid
    0.54
     MAGIC
    0.54
    Act Density 0.093%

    No Known Activations