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

    Neuronpedia

    INDEX
    Explanations

    specific references to magical elements or abilities in storytelling or fantasy contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Civilization
    -0.15
     Chapman
    -0.14
    aurus
    -0.14
    oplast
    -0.14
    idla
    -0.14
    strcasecmp
    -0.13
     slic
    -0.13
    emean
    -0.13
    acho
    -0.13
    ACE
    -0.13
    POSITIVE LOGITS
     sor
    0.28
     Magick
    0.28
     witch
    0.27
     Salem
    0.27
     Spells
    0.26
     magic
    0.26
     Witch
    0.26
     spells
    0.26
     witches
    0.26
     Conj
    0.25
    Act Density 0.109%

    No Known Activations