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

    Neuronpedia

    INDEX
    Explanations

    terms related to nuclear weapons and disarmament discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eid
    -0.15
    byt
    -0.15
    /misc
    -0.15
     Ellison
    -0.14
    çĸĨ
    -0.14
     kra
    -0.14
     Tarif
    -0.14
    printing
    -0.14
    itag
    -0.14
    apiro
    -0.14
    POSITIVE LOGITS
     nuclear
    0.28
     Nuclear
    0.26
    æł¸
    0.22
     disarm
    0.22
    uclear
    0.22
     proliferation
    0.21
     arms
    0.18
     Arms
    0.18
     plut
    0.18
    meld
    0.17
    Act Density 0.048%

    No Known Activations