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

    Neuronpedia

    INDEX
    Explanations

    words related to national security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to national security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sample
    -0.76
    amaz
    -0.73
    ken
    -0.71
    SHIP
    -0.71
    oven
    -0.69
    chrom
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    ãĥ£
    -0.65
    66666666
    -0.65
    bare
    -0.64
    POSITIVE LOGITS
     Advisor
    0.98
     adviser
    0.97
     advisor
    0.95
     Adviser
    0.92
    olitics
    0.88
    policy
    0.82
    aceutical
    0.81
     counterterrorism
    0.80
     posture
    0.79
     planners
    0.78
    Act Density 0.019%

    No Known Activations