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

    Neuronpedia

    INDEX
    Explanations

    terms related to weapons, especially nuclear weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of weapons, particularly nuclear and chemical weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Woodward
    -0.81
     Beckham
    -0.74
    noon
    -0.74
    athan
    -0.74
    Scotland
    -0.69
     Manz
    -0.68
    orse
    -0.66
    OVA
    -0.66
    vent
    -0.66
     Strawberry
    -0.65
    POSITIVE LOGITS
     weapons
    1.21
    chwitz
    0.99
     arsenal
    0.98
     weapon
    0.95
     weaponry
    0.95
    weapons
    0.93
    powder
    0.88
     weap
    0.88
     mathemat
    0.87
     pistols
    0.87
    Act Density 0.018%

    No Known Activations