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

    Neuronpedia

    INDEX
    Explanations

    phrases related to national security or public safety

    oai_token-act-pair · gpt-3.5-turbo

    references to national security and public safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ly
    -0.73
    Lot
    -0.72
    Mask
    -0.70
    ANN
    -0.67
    igs
    -0.65
     confess
    -0.64
     Zen
    -0.62
    married
    -0.62
    verse
    -0.62
     Canaver
    -0.61
    POSITIVE LOGITS
     wellbeing
    0.96
     deterrence
    0.87
    jriwal
    0.87
     crises
    0.86
     interests
    0.85
     preservation
    0.83
     objectives
    0.82
     liberties
    0.81
     endanger
    0.80
    rity
    0.80
    Act Density 0.224%

    No Known Activations