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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and related treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etxt
    -0.15
     Duty
    -0.14
    .EOF
    -0.14
    FFT
    -0.14
     Rescue
    -0.14
    URAL
    -0.13
    anggan
    -0.13
    _PATCH
    -0.13
    áºŃn
    -0.13
     fen
    -0.13
    POSITIVE LOGITS
     nuclear
    0.54
     Nuclear
    0.49
    uclear
    0.39
    æł¸
    0.37
     disarm
    0.36
     Arms
    0.33
     atomic
    0.33
     weapons
    0.32
     arms
    0.32
     Atomic
    0.30
    Act Density 0.024%

    No Known Activations