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

    Neuronpedia

    INDEX
    Explanations

    phrases related to nuclear technology

    oai_token-act-pair · gpt-3.5-turbo

    references to nuclear energy and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Row
    -0.75
    Preview
    -0.73
    AGES
    -0.73
    alties
    -0.73
    00200000
    -0.72
    haw
    -0.71
    lies
    -0.69
    olkien
    -0.69
    BACK
    -0.68
    olulu
    -0.67
    POSITIVE LOGITS
     deterrent
    0.98
     reactors
    0.95
     reactor
    0.95
     submarines
    0.94
     deterrence
    0.94
     submarine
    0.92
     weapons
    0.91
     warheads
    0.87
     disarm
    0.85
     missile
    0.85
    Act Density 0.046%

    No Known Activations