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

    Neuronpedia

    INDEX
    Explanations

    references to security measures

    oai_token-act-pair · gpt-3.5-turbo

    references to security personnel and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.82
    theless
    -0.78
    arget
    -0.75
    ufact
    -0.75
    alogy
    -0.75
    ãĥ£
    -0.73
    ohydrate
    -0.73
     Ago
    -0.72
    cipled
    -0.70
    ced
    -0.70
    POSITIVE LOGITS
     guards
    1.08
     personnel
    1.02
     clearance
    1.00
     checkpoints
    0.91
     enforcement
    0.88
     guard
    0.87
     security
    0.87
     screening
    0.85
     checkpoint
    0.80
     detail
    0.80
    Act Density 0.030%

    No Known Activations