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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear-related topics and treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤин
    -0.15
    unordered
    -0.14
    enville
    -0.14
    á»ĭ
    -0.13
     Passion
    -0.13
     Retail
    -0.13
    luž
    -0.13
    ç¿Ķ
    -0.13
     вк
    -0.13
    -Cal
    -0.13
    POSITIVE LOGITS
     safeguards
    0.33
     Nuclear
    0.32
     nuclear
    0.32
     Saf
    0.29
     Agency
    0.27
     inspections
    0.26
     inspectors
    0.26
     Atomic
    0.26
     safeguard
    0.25
     uranium
    0.24
    Act Density 0.011%

    No Known Activations