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

    Neuronpedia

    INDEX
    Explanations

    references to historical battles

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Battle" along with specific numeric designations associated with various content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IJ
    -0.66
    ure
    -0.62
    ATURE
    -0.61
     wee
    -0.60
    eller
    -0.60
     socket
    -0.60
    zzle
    -0.58
    ilk
    -0.57
    elled
    -0.57
    eus
    -0.56
    POSITIVE LOGITS
    cru
    1.24
     roy
    1.21
    cry
    1.14
    front
    1.11
     Royale
    1.11
    axe
    1.06
    mage
    1.03
    ments
    0.98
    fleet
    0.94
    fields
    0.93
    Act Density 0.054%

    No Known Activations