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

    Neuronpedia

    INDEX
    Explanations

    references to magic or magical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndProject
    -0.85
    RectangleBorder
    -0.83
    Personensuche
    -0.77
    :].
    -0.76
     useAppContext
    -0.72
     Giud
    -0.72
    osoba
    -0.70
    <>("
    -0.70
    principalColumn
    -0.68
    ("~/
    -0.67
    POSITIVE LOGITS
     magic
    2.93
     Magic
    2.67
    magic
    2.60
    Magic
    2.58
     MAGIC
    2.33
     magia
    2.21
     magical
    2.18
    MAGIC
    2.08
     magique
    2.02
    magical
    1.93
    Act Density 0.068%

    No Known Activations