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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andal
    -0.15
     Scanner
    -0.15
     Noise
    -0.14
    оÑĢов
    -0.14
    å¥
    -0.14
    CAA
    -0.14
     Anchor
    -0.14
     hel
    -0.14
     Magnet
    -0.13
     pseud
    -0.13
    POSITIVE LOGITS
     nuclear
    0.47
     atomic
    0.43
    uclear
    0.40
     Nuclear
    0.39
    æł¸
    0.38
     Atomic
    0.37
    Atomic
    0.33
    atomic
    0.33
     atom
    0.32
     اÙĦÙĨÙĪ
    0.30
    Act Density 0.110%

    No Known Activations