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

    Neuronpedia

    INDEX
    Explanations

    words related to security and surveillance

    oai_token-act-pair · gpt-3.5-turbo

    references to security-related topics and measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.87
    igible
    -0.85
    ufact
    -0.83
    yss
    -0.78
    sembly
    -0.78
    phrine
    -0.76
    liam
    -0.72
    kson
    -0.71
    alogy
    -0.69
    cipled
    -0.69
    POSITIVE LOGITS
     clearance
    0.98
     guards
    0.98
     checkpoints
    0.96
     personnel
    0.91
     breaches
    0.90
     guard
    0.88
     checkpoint
    0.86
     measures
    0.83
     forces
    0.83
     screening
    0.82
    Act Density 0.047%

    No Known Activations