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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear power and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LoadIdentity
    -0.16
    CTX
    -0.16
    gem
    -0.15
    ableView
    -0.15
    chaft
    -0.14
    ekil
    -0.14
    коном
    -0.14
    åIJ¾
    -0.14
    ÑĤин
    -0.14
    aurus
    -0.14
    POSITIVE LOGITS
    -powered
    0.23
     weapons
    0.20
     power
    0.20
     weapon
    0.19
     medicine
    0.18
    powered
    0.18
     waste
    0.18
     powered
    0.17
    -power
    0.16
     Weapons
    0.16
    Act Density 0.012%

    No Known Activations