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

    Neuronpedia

    INDEX
    Explanations

    terms related to nuclear weapons and their risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ø·Ùģ
    -0.15
    _NODES
    -0.15
     giả
    -0.15
    udo
    -0.14
    ksiyon
    -0.14
     Kushner
    -0.14
     Ñĩин
    -0.14
    inho
    -0.13
    asting
    -0.13
    ech
    -0.13
    POSITIVE LOGITS
    teri
    0.16
    panse
    0.16
    vig
    0.15
    owi
    0.15
    ootball
    0.15
    strate
    0.14
     Advocate
    0.14
    GetInstance
    0.14
    emm
    0.14
    vailable
    0.14
    Act Density 0.014%

    No Known Activations